Saxton Publishing Technical Documentation - User contributions [en]

Righting Sentences User Guide - 4.0

2026-02-07T00:14:52Z

Saxtonmd77: /* 14. Data and Privacy */

'''Righting Sentences''' — User Guide (v4.0)

Last updated: February 2026

Production URL: https://righting-sentences-573737403792.us-east1.run.app/

__TOC__

== 1. Purpose and Scope ==
Righting Sentences is a web-based chat application that generates AI text that reads more like standard written English. This application is a data science project that includes a unique two-pass editorial system, the Morey Language Model which automatically detects and removes AI-typical language patterns. Usage improves the Morey Language Model, an editorial system that eventually will include a fine-tuned foundational LLM.

== 2. Access and Authentication ==

=== 2.1 Google account required ===
To use the application, you must sign in with a Google account.

=== 2.2 Invitation-only access ===
Access is provided by invitation. If you cannot sign in or do not see the application after signing in, contact the administrator at https://saxtonpublishing.com/contact/.

=== 2.3 Sign in ===
# Navigate to the production URL
# Select '''Sign in with Google'''
# Complete Google authentication
# After sign-in, you will see the main chat interface

== 3. User Interface ==

=== 3.1 Layout overview ===
The interface has two main areas:
* '''Left sidebar''' - Chat history, model selector, and menu
* '''Main chat window''' - Conversation view and message input

=== 3.2 Left Sidebar ===

==== Chat history list ====
Each row shows:
* The conversation title
* The model used for that conversation

To open a conversation, select it from the list.

==== Model selector ====
Choose which AI model to use for new conversations:
* '''GPT-4o''' - OpenAI's most famous model
* '''GPT-5.2 Pro''' - OpenAI's advanced reasoning model
* '''Claude Sonnet 4.5''' - Anthropic's general model
* '''Gemini-3 Flash''' - Google's fast model

'''Note''' - Models cannot be changed mid-conversation. Start a new chat to use a different model.

==== Menu items ====
* '''Account''' - View your profile and sign out
* '''Settings''' - Theme, colors, and custom instructions
* '''Insights''' - Editorial analytics dashboard
* '''Help''' - Link to documentation
* '''Sign Out''' - End your session

=== 3.3 Main Chat Window ===

==== Header ====
Shows the conversation title and current model badge.

==== Messages ====
* Your messages appear on the right
* Assistant messages appear on the left
* Hover over assistant messages to reveal the copy button

==== Message input ====
Type your message and press Enter or click Send.

== 4. Sending Messages ==

=== 4.1 Basic messaging ===
# Type your message in the input field
# Press '''Enter''' or click '''Send'''
# Wait for the assistant to respond

=== 4.2 Multi-line messages ===
Press '''Shift+Enter''' to create a new line without sending.

=== 4.3 Stop generation ===
While the assistant is responding, click '''Stop''' to halt generation early.

== 5. Options Menu ==

The '''Options''' button inside the message input area provides access to:
* File uploads
* Prompt templates
* Quick actions

=== 5.1 Opening Options ===
Click the '''Options''' button to reveal the dropdown menu.

== 6. File Uploads ==

=== 6.1 Upload a file ===
# Click '''Options'''
# Select '''Upload files'''
# Choose one or more files

=== 6.2 Supported file types ===
* '''Text:''' .txt, .md, .csv, .tsv, .json
* '''Documents:''' .pdf, .doc, .docx
* '''Presentations:''' .ppt, .pptx
* '''Spreadsheets:''' .xls, .xlsx
* '''Images:''' .png, .jpg, .gif, .webp, .bmp, .tiff

=== 6.3 File status ===
Uploaded files appear as chips above the input:
* '''Uploaded''' - File received
* '''Parsed''' - Text extracted and available to the model

=== 6.4 Remove a file ===
Click the '''×''' on the file chip to remove it from the conversation.

=== 6.5 File size limit ===
Maximum upload size is 25 MB per file.

== 7. Prompt Templates ==

Templates provide structured prompts for common content types.

=== 7.1 Using a template ===
# Click '''Options'''
# Select a template from the list
# The template badge appears above the input
# Type your specific content or context
# Send your message

=== 7.2 Available templates ===

==== Landing Pages ====
{| class="wikitable"
! Template !! Description
|-
| Locations || Global offices and delivery centers
|-
| Services || Service overview
|-
| Industries || Industry overview or specialization page
|-
| Leadership || Leadership team
|-
| Clients || Client portfolio
|}

==== Case Studies ====
{| class="wikitable"
! Template !! Description
|-
| Case Study (PPT) || PowerPoint, single-page case study
|-
| Case Study (Website) || SEO-optimized case study with KPIs
|}

=== 7.3 Template behavior ===
* Templates automatically use '''Google Gemini''' for optimal results
* The template badge shows which template is active
* Click '''×''' on the badge to clear the template

== 8. Quick Actions ==

Quick actions transform the previous AI response with one click.

=== 8.1 Available quick actions ===
{| class="wikitable"
! Action !! Effect
|-
| Make it shorter || Condense to ~50% of original length
|-
| Make it more formal || Increase professional tone
|-
| Simplify this || Make clearer and more accessible
|-
| Expand on this || Add detail and elaboration
|}

=== 8.2 Using quick actions ===
# You must write a prompt and receive a message before you can run a quick action
# Click '''Options'''
# Select a quick action
# The action executes using Gemini 3

== 9. Editorial Insights ==

The Insights dashboard shows a user's editorial analytics.

=== 9.1 Accessing Insights ===
# Open the sidebar
# Click '''Insights''' in the menu

=== 9.2 Metrics displayed ===
* '''Total Messages''' - Number of messages processed
* '''Passed''' - Messages without AI pattern violations
* '''Violations''' - Messages where patterns were detected and corrected
* '''Pass Rate''' - Percentage of clean messages

=== 9.3 Top Violations ===
Shows the most common AI-typical words detected in your conversations.

=== 9.4 Recent Corrections ===
Examples of recent messages where the editorial system improved the output.

== 10. Conversation Export ==

Export your conversations.

=== 10.1 Export formats ===
* '''Markdown''' - Formatted text file that can be rendered in a Markdown reader
* '''JSON''' - Structured data

=== 10.2 How to export ===
# Open the conversation you want to export
# Click the '''Export''' button in the header
# Select '''Markdown''' or '''JSON'''
# The file downloads automatically

== 11. Settings ==

=== 11.1 Theme ===
* '''Light''' - Light background
* '''Dark''' - Dark background
* '''System''' - Match your operating system preference

=== 11.2 Primary color ===
Choose an accent color for buttons and highlights.

=== 11.3 Custom instructions ===
Provide information about your personal preferences that the AI assistant should remember. This is information about the user that helps the AI write more personalized responses.

=== 11.4 LLM instructions ===
Add rules for how the AI assistant should respond. This includes additional banned words, style, tone, or other formatting specifics.

== 12. The Two-Pass Editorial System ==

Righting Sentences uses a two-pass system to improve AI output.

=== 12.1 How it works ===
# '''Pass 1:''' The AI generates a typical response for LLM models
# '''Detection:''' The system identifies AI-typical patterns
# '''Pass 2:''' The AI regenerates with stricter guidelines
# '''Post-processing:''' Any remaining issues are cleaned programmatically

== 13. Troubleshooting ==

=== 13.1 I cannot sign in ===
* Confirm you are using a Google account
* Confirm your account has been invited
* Contact Saxton Publishing if the problem persists

=== 13.2 I cannot change the model ===
Models cannot be changed mid-conversation. Start a new chat to use a different model.

=== 13.3 Quick actions are not available ===
Quick actions require at least one response to a prompt in the conversation. Send a message first, then use quick actions.

=== 13.4 Template is not working ===
* Ensure the template badge is visible above the input
* Templates require you to provide context in your message
* If issues persist, clear the template and try again

=== 13.5 File upload fails ===
* Check that the file is under 25 MB
* Verify the file type is supported
* Contact the administrator if errors persist

== 14. Data and Privacy ==

=== 14.1 What is stored ===
* Conversations and messages
* Uploaded files
* Editorial logs (for system improvement)

=== 14.2 Where data is stored ===
* Google Cloud Firestore (conversations, metadata)
* Google Cloud Storage (uploaded files)

=== 14.3 Third-party providers ===
Messages are sent to the selected model provider (OpenAI, Anthropic, or Google) to generate responses.

== 15. Deleting Data ==

* To delete the message from a user's storage, click the trash can symbol next to the message you'd like to delete
* To delete your data from the project, contact Saxton Publishing

----
''Righting Sentences is developed by Saxton Publishing.''

[[Category:Righting Sentences]]
[[Category:User Guide]]

Righting Sentences User Guide - 4.0

2026-02-07T00:12:23Z

Saxtonmd77: /* 13.3 Quick actions are not available */

'''Righting Sentences''' — User Guide (v4.0)

Last updated: February 2026

Production URL: https://righting-sentences-573737403792.us-east1.run.app/

__TOC__

== 1. Purpose and Scope ==
Righting Sentences is a web-based chat application that generates AI text that reads more like standard written English. This application is a data science project that includes a unique two-pass editorial system, the Morey Language Model which automatically detects and removes AI-typical language patterns. Usage improves the Morey Language Model, an editorial system that eventually will include a fine-tuned foundational LLM.

== 2. Access and Authentication ==

=== 2.1 Google account required ===
To use the application, you must sign in with a Google account.

=== 2.2 Invitation-only access ===
Access is provided by invitation. If you cannot sign in or do not see the application after signing in, contact the administrator at https://saxtonpublishing.com/contact/.

=== 2.3 Sign in ===
# Navigate to the production URL
# Select '''Sign in with Google'''
# Complete Google authentication
# After sign-in, you will see the main chat interface

== 3. User Interface ==

=== 3.1 Layout overview ===
The interface has two main areas:
* '''Left sidebar''' - Chat history, model selector, and menu
* '''Main chat window''' - Conversation view and message input

=== 3.2 Left Sidebar ===

==== Chat history list ====
Each row shows:
* The conversation title
* The model used for that conversation

To open a conversation, select it from the list.

==== Model selector ====
Choose which AI model to use for new conversations:
* '''GPT-4o''' - OpenAI's most famous model
* '''GPT-5.2 Pro''' - OpenAI's advanced reasoning model
* '''Claude Sonnet 4.5''' - Anthropic's general model
* '''Gemini-3 Flash''' - Google's fast model

'''Note''' - Models cannot be changed mid-conversation. Start a new chat to use a different model.

==== Menu items ====
* '''Account''' - View your profile and sign out
* '''Settings''' - Theme, colors, and custom instructions
* '''Insights''' - Editorial analytics dashboard
* '''Help''' - Link to documentation
* '''Sign Out''' - End your session

=== 3.3 Main Chat Window ===

==== Header ====
Shows the conversation title and current model badge.

==== Messages ====
* Your messages appear on the right
* Assistant messages appear on the left
* Hover over assistant messages to reveal the copy button

==== Message input ====
Type your message and press Enter or click Send.

== 4. Sending Messages ==

=== 4.1 Basic messaging ===
# Type your message in the input field
# Press '''Enter''' or click '''Send'''
# Wait for the assistant to respond

=== 4.2 Multi-line messages ===
Press '''Shift+Enter''' to create a new line without sending.

=== 4.3 Stop generation ===
While the assistant is responding, click '''Stop''' to halt generation early.

== 5. Options Menu ==

The '''Options''' button inside the message input area provides access to:
* File uploads
* Prompt templates
* Quick actions

=== 5.1 Opening Options ===
Click the '''Options''' button to reveal the dropdown menu.

== 6. File Uploads ==

=== 6.1 Upload a file ===
# Click '''Options'''
# Select '''Upload files'''
# Choose one or more files

=== 6.2 Supported file types ===
* '''Text:''' .txt, .md, .csv, .tsv, .json
* '''Documents:''' .pdf, .doc, .docx
* '''Presentations:''' .ppt, .pptx
* '''Spreadsheets:''' .xls, .xlsx
* '''Images:''' .png, .jpg, .gif, .webp, .bmp, .tiff

=== 6.3 File status ===
Uploaded files appear as chips above the input:
* '''Uploaded''' - File received
* '''Parsed''' - Text extracted and available to the model

=== 6.4 Remove a file ===
Click the '''×''' on the file chip to remove it from the conversation.

=== 6.5 File size limit ===
Maximum upload size is 25 MB per file.

== 7. Prompt Templates ==

Templates provide structured prompts for common content types.

=== 7.1 Using a template ===
# Click '''Options'''
# Select a template from the list
# The template badge appears above the input
# Type your specific content or context
# Send your message

=== 7.2 Available templates ===

==== Landing Pages ====
{| class="wikitable"
! Template !! Description
|-
| Locations || Global offices and delivery centers
|-
| Services || Service overview
|-
| Industries || Industry overview or specialization page
|-
| Leadership || Leadership team
|-
| Clients || Client portfolio
|}

==== Case Studies ====
{| class="wikitable"
! Template !! Description
|-
| Case Study (PPT) || PowerPoint, single-page case study
|-
| Case Study (Website) || SEO-optimized case study with KPIs
|}

=== 7.3 Template behavior ===
* Templates automatically use '''Google Gemini''' for optimal results
* The template badge shows which template is active
* Click '''×''' on the badge to clear the template

== 8. Quick Actions ==

Quick actions transform the previous AI response with one click.

=== 8.1 Available quick actions ===
{| class="wikitable"
! Action !! Effect
|-
| Make it shorter || Condense to ~50% of original length
|-
| Make it more formal || Increase professional tone
|-
| Simplify this || Make clearer and more accessible
|-
| Expand on this || Add detail and elaboration
|}

=== 8.2 Using quick actions ===
# You must write a prompt and receive a message before you can run a quick action
# Click '''Options'''
# Select a quick action
# The action executes using Gemini 3

== 9. Editorial Insights ==

The Insights dashboard shows a user's editorial analytics.

=== 9.1 Accessing Insights ===
# Open the sidebar
# Click '''Insights''' in the menu

=== 9.2 Metrics displayed ===
* '''Total Messages''' - Number of messages processed
* '''Passed''' - Messages without AI pattern violations
* '''Violations''' - Messages where patterns were detected and corrected
* '''Pass Rate''' - Percentage of clean messages

=== 9.3 Top Violations ===
Shows the most common AI-typical words detected in your conversations.

=== 9.4 Recent Corrections ===
Examples of recent messages where the editorial system improved the output.

== 10. Conversation Export ==

Export your conversations.

=== 10.1 Export formats ===
* '''Markdown''' - Formatted text file that can be rendered in a Markdown reader
* '''JSON''' - Structured data

=== 10.2 How to export ===
# Open the conversation you want to export
# Click the '''Export''' button in the header
# Select '''Markdown''' or '''JSON'''
# The file downloads automatically

== 11. Settings ==

=== 11.1 Theme ===
* '''Light''' - Light background
* '''Dark''' - Dark background
* '''System''' - Match your operating system preference

=== 11.2 Primary color ===
Choose an accent color for buttons and highlights.

=== 11.3 Custom instructions ===
Provide information about your personal preferences that the AI assistant should remember. This is information about the user that helps the AI write more personalized responses.

=== 11.4 LLM instructions ===
Add rules for how the AI assistant should respond. This includes additional banned words, style, tone, or other formatting specifics.

== 12. The Two-Pass Editorial System ==

Righting Sentences uses a two-pass system to improve AI output.

=== 12.1 How it works ===
# '''Pass 1:''' The AI generates a typical response for LLM models
# '''Detection:''' The system identifies AI-typical patterns
# '''Pass 2:''' The AI regenerates with stricter guidelines
# '''Post-processing:''' Any remaining issues are cleaned programmatically

== 13. Troubleshooting ==

=== 13.1 I cannot sign in ===
* Confirm you are using a Google account
* Confirm your account has been invited
* Contact Saxton Publishing if the problem persists

=== 13.2 I cannot change the model ===
Models cannot be changed mid-conversation. Start a new chat to use a different model.

=== 13.3 Quick actions are not available ===
Quick actions require at least one response to a prompt in the conversation. Send a message first, then use quick actions.

=== 13.4 Template is not working ===
* Ensure the template badge is visible above the input
* Templates require you to provide context in your message
* If issues persist, clear the template and try again

=== 13.5 File upload fails ===
* Check that the file is under 25 MB
* Verify the file type is supported
* Contact the administrator if errors persist

== 14. Data and Privacy ==

=== 14.1 What is stored ===
* Conversations and messages
* Uploaded files
* Editorial logs (for system improvement)

=== 14.2 Where data is stored ===
* Google Cloud Firestore (conversations, metadata)
* Google Cloud Storage (uploaded files)

=== 14.3 Third-party providers ===
Messages are sent to the selected model provider (OpenAI, Anthropic, or Google) to generate responses.

----
''Righting Sentences is developed by Saxton Publishing.''

[[Category:Righting Sentences]]
[[Category:User Guide]]

Righting Sentences User Guide - 4.0

2026-02-07T00:11:35Z

Saxtonmd77: /* 12. The Two-Pass Editorial System */

'''Righting Sentences''' — User Guide (v4.0)

Last updated: February 2026

Production URL: https://righting-sentences-573737403792.us-east1.run.app/

__TOC__

== 1. Purpose and Scope ==
Righting Sentences is a web-based chat application that generates AI text that reads more like standard written English. This application is a data science project that includes a unique two-pass editorial system, the Morey Language Model which automatically detects and removes AI-typical language patterns. Usage improves the Morey Language Model, an editorial system that eventually will include a fine-tuned foundational LLM.

== 2. Access and Authentication ==

=== 2.1 Google account required ===
To use the application, you must sign in with a Google account.

=== 2.2 Invitation-only access ===
Access is provided by invitation. If you cannot sign in or do not see the application after signing in, contact the administrator at https://saxtonpublishing.com/contact/.

=== 2.3 Sign in ===
# Navigate to the production URL
# Select '''Sign in with Google'''
# Complete Google authentication
# After sign-in, you will see the main chat interface

== 3. User Interface ==

=== 3.1 Layout overview ===
The interface has two main areas:
* '''Left sidebar''' - Chat history, model selector, and menu
* '''Main chat window''' - Conversation view and message input

=== 3.2 Left Sidebar ===

==== Chat history list ====
Each row shows:
* The conversation title
* The model used for that conversation

To open a conversation, select it from the list.

==== Model selector ====
Choose which AI model to use for new conversations:
* '''GPT-4o''' - OpenAI's most famous model
* '''GPT-5.2 Pro''' - OpenAI's advanced reasoning model
* '''Claude Sonnet 4.5''' - Anthropic's general model
* '''Gemini-3 Flash''' - Google's fast model

'''Note''' - Models cannot be changed mid-conversation. Start a new chat to use a different model.

==== Menu items ====
* '''Account''' - View your profile and sign out
* '''Settings''' - Theme, colors, and custom instructions
* '''Insights''' - Editorial analytics dashboard
* '''Help''' - Link to documentation
* '''Sign Out''' - End your session

=== 3.3 Main Chat Window ===

==== Header ====
Shows the conversation title and current model badge.

==== Messages ====
* Your messages appear on the right
* Assistant messages appear on the left
* Hover over assistant messages to reveal the copy button

==== Message input ====
Type your message and press Enter or click Send.

== 4. Sending Messages ==

=== 4.1 Basic messaging ===
# Type your message in the input field
# Press '''Enter''' or click '''Send'''
# Wait for the assistant to respond

=== 4.2 Multi-line messages ===
Press '''Shift+Enter''' to create a new line without sending.

=== 4.3 Stop generation ===
While the assistant is responding, click '''Stop''' to halt generation early.

== 5. Options Menu ==

The '''Options''' button inside the message input area provides access to:
* File uploads
* Prompt templates
* Quick actions

=== 5.1 Opening Options ===
Click the '''Options''' button to reveal the dropdown menu.

== 6. File Uploads ==

=== 6.1 Upload a file ===
# Click '''Options'''
# Select '''Upload files'''
# Choose one or more files

=== 6.2 Supported file types ===
* '''Text:''' .txt, .md, .csv, .tsv, .json
* '''Documents:''' .pdf, .doc, .docx
* '''Presentations:''' .ppt, .pptx
* '''Spreadsheets:''' .xls, .xlsx
* '''Images:''' .png, .jpg, .gif, .webp, .bmp, .tiff

=== 6.3 File status ===
Uploaded files appear as chips above the input:
* '''Uploaded''' - File received
* '''Parsed''' - Text extracted and available to the model

=== 6.4 Remove a file ===
Click the '''×''' on the file chip to remove it from the conversation.

=== 6.5 File size limit ===
Maximum upload size is 25 MB per file.

== 7. Prompt Templates ==

Templates provide structured prompts for common content types.

=== 7.1 Using a template ===
# Click '''Options'''
# Select a template from the list
# The template badge appears above the input
# Type your specific content or context
# Send your message

=== 7.2 Available templates ===

==== Landing Pages ====
{| class="wikitable"
! Template !! Description
|-
| Locations || Global offices and delivery centers
|-
| Services || Service overview
|-
| Industries || Industry overview or specialization page
|-
| Leadership || Leadership team
|-
| Clients || Client portfolio
|}

==== Case Studies ====
{| class="wikitable"
! Template !! Description
|-
| Case Study (PPT) || PowerPoint, single-page case study
|-
| Case Study (Website) || SEO-optimized case study with KPIs
|}

=== 7.3 Template behavior ===
* Templates automatically use '''Google Gemini''' for optimal results
* The template badge shows which template is active
* Click '''×''' on the badge to clear the template

== 8. Quick Actions ==

Quick actions transform the previous AI response with one click.

=== 8.1 Available quick actions ===
{| class="wikitable"
! Action !! Effect
|-
| Make it shorter || Condense to ~50% of original length
|-
| Make it more formal || Increase professional tone
|-
| Simplify this || Make clearer and more accessible
|-
| Expand on this || Add detail and elaboration
|}

=== 8.2 Using quick actions ===
# You must write a prompt and receive a message before you can run a quick action
# Click '''Options'''
# Select a quick action
# The action executes using Gemini 3

== 9. Editorial Insights ==

The Insights dashboard shows a user's editorial analytics.

=== 9.1 Accessing Insights ===
# Open the sidebar
# Click '''Insights''' in the menu

=== 9.2 Metrics displayed ===
* '''Total Messages''' - Number of messages processed
* '''Passed''' - Messages without AI pattern violations
* '''Violations''' - Messages where patterns were detected and corrected
* '''Pass Rate''' - Percentage of clean messages

=== 9.3 Top Violations ===
Shows the most common AI-typical words detected in your conversations.

=== 9.4 Recent Corrections ===
Examples of recent messages where the editorial system improved the output.

== 10. Conversation Export ==

Export your conversations.

=== 10.1 Export formats ===
* '''Markdown''' - Formatted text file that can be rendered in a Markdown reader
* '''JSON''' - Structured data

=== 10.2 How to export ===
# Open the conversation you want to export
# Click the '''Export''' button in the header
# Select '''Markdown''' or '''JSON'''
# The file downloads automatically

== 11. Settings ==

=== 11.1 Theme ===
* '''Light''' - Light background
* '''Dark''' - Dark background
* '''System''' - Match your operating system preference

=== 11.2 Primary color ===
Choose an accent color for buttons and highlights.

=== 11.3 Custom instructions ===
Provide information about your personal preferences that the AI assistant should remember. This is information about the user that helps the AI write more personalized responses.

=== 11.4 LLM instructions ===
Add rules for how the AI assistant should respond. This includes additional banned words, style, tone, or other formatting specifics.

== 12. The Two-Pass Editorial System ==

Righting Sentences uses a two-pass system to improve AI output.

=== 12.1 How it works ===
# '''Pass 1:''' The AI generates a typical response for LLM models
# '''Detection:''' The system identifies AI-typical patterns
# '''Pass 2:''' The AI regenerates with stricter guidelines
# '''Post-processing:''' Any remaining issues are cleaned programmatically

== 13. Troubleshooting ==

=== 13.1 I cannot sign in ===
* Confirm you are using a Google account
* Confirm your account has been invited
* Contact Saxton Publishing if the problem persists

=== 13.2 I cannot change the model ===
Models cannot be changed mid-conversation. Start a new chat to use a different model.

=== 13.3 Quick actions are not available ===
Quick actions require at least one assistant message in the conversation. Send a message first, then use quick actions.

=== 13.4 Template is not working ===
* Ensure the template badge is visible above the input
* Templates require you to provide context in your message
* If issues persist, clear the template and try again

=== 13.5 File upload fails ===
* Check that the file is under 25 MB
* Verify the file type is supported
* Contact the administrator if errors persist

== 14. Data and Privacy ==

=== 14.1 What is stored ===
* Conversations and messages
* Uploaded files
* Editorial logs (for system improvement)

=== 14.2 Where data is stored ===
* Google Cloud Firestore (conversations, metadata)
* Google Cloud Storage (uploaded files)

=== 14.3 Third-party providers ===
Messages are sent to the selected model provider (OpenAI, Anthropic, or Google) to generate responses.

----
''Righting Sentences is developed by Saxton Publishing.''

[[Category:Righting Sentences]]
[[Category:User Guide]]

Righting Sentences User Guide - 4.0

2026-02-07T00:09:53Z

Saxtonmd77: /* 11.4 LLM instructions */

'''Righting Sentences''' — User Guide (v4.0)

Last updated: February 2026

Production URL: https://righting-sentences-573737403792.us-east1.run.app/

__TOC__

== 1. Purpose and Scope ==
Righting Sentences is a web-based chat application that generates AI text that reads more like standard written English. This application is a data science project that includes a unique two-pass editorial system, the Morey Language Model which automatically detects and removes AI-typical language patterns. Usage improves the Morey Language Model, an editorial system that eventually will include a fine-tuned foundational LLM.

== 2. Access and Authentication ==

=== 2.1 Google account required ===
To use the application, you must sign in with a Google account.

=== 2.2 Invitation-only access ===
Access is provided by invitation. If you cannot sign in or do not see the application after signing in, contact the administrator at https://saxtonpublishing.com/contact/.

=== 2.3 Sign in ===
# Navigate to the production URL
# Select '''Sign in with Google'''
# Complete Google authentication
# After sign-in, you will see the main chat interface

== 3. User Interface ==

=== 3.1 Layout overview ===
The interface has two main areas:
* '''Left sidebar''' - Chat history, model selector, and menu
* '''Main chat window''' - Conversation view and message input

=== 3.2 Left Sidebar ===

==== Chat history list ====
Each row shows:
* The conversation title
* The model used for that conversation

To open a conversation, select it from the list.

==== Model selector ====
Choose which AI model to use for new conversations:
* '''GPT-4o''' - OpenAI's most famous model
* '''GPT-5.2 Pro''' - OpenAI's advanced reasoning model
* '''Claude Sonnet 4.5''' - Anthropic's general model
* '''Gemini-3 Flash''' - Google's fast model

'''Note''' - Models cannot be changed mid-conversation. Start a new chat to use a different model.

==== Menu items ====
* '''Account''' - View your profile and sign out
* '''Settings''' - Theme, colors, and custom instructions
* '''Insights''' - Editorial analytics dashboard
* '''Help''' - Link to documentation
* '''Sign Out''' - End your session

=== 3.3 Main Chat Window ===

==== Header ====
Shows the conversation title and current model badge.

==== Messages ====
* Your messages appear on the right
* Assistant messages appear on the left
* Hover over assistant messages to reveal the copy button

==== Message input ====
Type your message and press Enter or click Send.

== 4. Sending Messages ==

=== 4.1 Basic messaging ===
# Type your message in the input field
# Press '''Enter''' or click '''Send'''
# Wait for the assistant to respond

=== 4.2 Multi-line messages ===
Press '''Shift+Enter''' to create a new line without sending.

=== 4.3 Stop generation ===
While the assistant is responding, click '''Stop''' to halt generation early.

== 5. Options Menu ==

The '''Options''' button inside the message input area provides access to:
* File uploads
* Prompt templates
* Quick actions

=== 5.1 Opening Options ===
Click the '''Options''' button to reveal the dropdown menu.

== 6. File Uploads ==

=== 6.1 Upload a file ===
# Click '''Options'''
# Select '''Upload files'''
# Choose one or more files

=== 6.2 Supported file types ===
* '''Text:''' .txt, .md, .csv, .tsv, .json
* '''Documents:''' .pdf, .doc, .docx
* '''Presentations:''' .ppt, .pptx
* '''Spreadsheets:''' .xls, .xlsx
* '''Images:''' .png, .jpg, .gif, .webp, .bmp, .tiff

=== 6.3 File status ===
Uploaded files appear as chips above the input:
* '''Uploaded''' - File received
* '''Parsed''' - Text extracted and available to the model

=== 6.4 Remove a file ===
Click the '''×''' on the file chip to remove it from the conversation.

=== 6.5 File size limit ===
Maximum upload size is 25 MB per file.

== 7. Prompt Templates ==

Templates provide structured prompts for common content types.

=== 7.1 Using a template ===
# Click '''Options'''
# Select a template from the list
# The template badge appears above the input
# Type your specific content or context
# Send your message

=== 7.2 Available templates ===

==== Landing Pages ====
{| class="wikitable"
! Template !! Description
|-
| Locations || Global offices and delivery centers
|-
| Services || Service overview
|-
| Industries || Industry overview or specialization page
|-
| Leadership || Leadership team
|-
| Clients || Client portfolio
|}

==== Case Studies ====
{| class="wikitable"
! Template !! Description
|-
| Case Study (PPT) || PowerPoint, single-page case study
|-
| Case Study (Website) || SEO-optimized case study with KPIs
|}

=== 7.3 Template behavior ===
* Templates automatically use '''Google Gemini''' for optimal results
* The template badge shows which template is active
* Click '''×''' on the badge to clear the template

== 8. Quick Actions ==

Quick actions transform the previous AI response with one click.

=== 8.1 Available quick actions ===
{| class="wikitable"
! Action !! Effect
|-
| Make it shorter || Condense to ~50% of original length
|-
| Make it more formal || Increase professional tone
|-
| Simplify this || Make clearer and more accessible
|-
| Expand on this || Add detail and elaboration
|}

=== 8.2 Using quick actions ===
# You must write a prompt and receive a message before you can run a quick action
# Click '''Options'''
# Select a quick action
# The action executes using Gemini 3

== 9. Editorial Insights ==

The Insights dashboard shows a user's editorial analytics.

=== 9.1 Accessing Insights ===
# Open the sidebar
# Click '''Insights''' in the menu

=== 9.2 Metrics displayed ===
* '''Total Messages''' - Number of messages processed
* '''Passed''' - Messages without AI pattern violations
* '''Violations''' - Messages where patterns were detected and corrected
* '''Pass Rate''' - Percentage of clean messages

=== 9.3 Top Violations ===
Shows the most common AI-typical words detected in your conversations.

=== 9.4 Recent Corrections ===
Examples of recent messages where the editorial system improved the output.

== 10. Conversation Export ==

Export your conversations.

=== 10.1 Export formats ===
* '''Markdown''' - Formatted text file that can be rendered in a Markdown reader
* '''JSON''' - Structured data

=== 10.2 How to export ===
# Open the conversation you want to export
# Click the '''Export''' button in the header
# Select '''Markdown''' or '''JSON'''
# The file downloads automatically

== 11. Settings ==

=== 11.1 Theme ===
* '''Light''' - Light background
* '''Dark''' - Dark background
* '''System''' - Match your operating system preference

=== 11.2 Primary color ===
Choose an accent color for buttons and highlights.

=== 11.3 Custom instructions ===
Provide information about your personal preferences that the AI assistant should remember. This is information about the user that helps the AI write more personalized responses.

=== 11.4 LLM instructions ===
Add rules for how the AI assistant should respond. This includes additional banned words, style, tone, or other formatting specifics.

== 12. The Two-Pass Editorial System ==

Righting Sentences uses a unique two-pass system to improve AI output.

=== 12.1 How it works ===
# '''Pass 1:''' The AI generates a natural response
# '''Detection:''' The system identifies AI-typical patterns:
#* Banned words (e.g., "utilize", "landscape", "delve")
#* Three-part lists (triads)
#* Rhetorical patterns (e.g., "It's not X, it's Y")
# '''Pass 2:''' The AI regenerates with stricter guidelines
# '''Post-processing:''' Any remaining issues are cleaned programmatically

=== 12.2 Why it matters ===
AI models tend to overuse certain words and patterns that make text sound artificial. The editorial system produces writing that sounds more natural and human-like.

=== 12.3 Banned words ===
The system currently flags: utilize, landscape, unlock, critical, guardrails, tracks, shape, shift, teams, delve, tapestry.

=== 12.4 Triad exceptions ===
Some three-part phrases are culturally significant and exempt from editing:
* "executive, legislative, and judicial"
* "life, liberty, and the pursuit of happiness"
* "red, white, and blue"

== 13. Troubleshooting ==

=== 13.1 I cannot sign in ===
* Confirm you are using a Google account
* Confirm your account has been invited
* Contact Saxton Publishing if the problem persists

=== 13.2 I cannot change the model ===
Models cannot be changed mid-conversation. Start a new chat to use a different model.

=== 13.3 Quick actions are not available ===
Quick actions require at least one assistant message in the conversation. Send a message first, then use quick actions.

=== 13.4 Template is not working ===
* Ensure the template badge is visible above the input
* Templates require you to provide context in your message
* If issues persist, clear the template and try again

=== 13.5 File upload fails ===
* Check that the file is under 25 MB
* Verify the file type is supported
* Contact the administrator if errors persist

== 14. Data and Privacy ==

=== 14.1 What is stored ===
* Conversations and messages
* Uploaded files
* Editorial logs (for system improvement)

=== 14.2 Where data is stored ===
* Google Cloud Firestore (conversations, metadata)
* Google Cloud Storage (uploaded files)

=== 14.3 Third-party providers ===
Messages are sent to the selected model provider (OpenAI, Anthropic, or Google) to generate responses.

----
''Righting Sentences is developed by Saxton Publishing.''

[[Category:Righting Sentences]]
[[Category:User Guide]]

Righting Sentences User Guide - 4.0

2026-02-07T00:09:12Z

Saxtonmd77: /* 11.3 Custom instructions */

'''Righting Sentences''' — User Guide (v4.0)

Last updated: February 2026

Production URL: https://righting-sentences-573737403792.us-east1.run.app/

__TOC__

== 1. Purpose and Scope ==
Righting Sentences is a web-based chat application that generates AI text that reads more like standard written English. This application is a data science project that includes a unique two-pass editorial system, the Morey Language Model which automatically detects and removes AI-typical language patterns. Usage improves the Morey Language Model, an editorial system that eventually will include a fine-tuned foundational LLM.

== 2. Access and Authentication ==

=== 2.1 Google account required ===
To use the application, you must sign in with a Google account.

=== 2.2 Invitation-only access ===
Access is provided by invitation. If you cannot sign in or do not see the application after signing in, contact the administrator at https://saxtonpublishing.com/contact/.

=== 2.3 Sign in ===
# Navigate to the production URL
# Select '''Sign in with Google'''
# Complete Google authentication
# After sign-in, you will see the main chat interface

== 3. User Interface ==

=== 3.1 Layout overview ===
The interface has two main areas:
* '''Left sidebar''' - Chat history, model selector, and menu
* '''Main chat window''' - Conversation view and message input

=== 3.2 Left Sidebar ===

==== Chat history list ====
Each row shows:
* The conversation title
* The model used for that conversation

To open a conversation, select it from the list.

==== Model selector ====
Choose which AI model to use for new conversations:
* '''GPT-4o''' - OpenAI's most famous model
* '''GPT-5.2 Pro''' - OpenAI's advanced reasoning model
* '''Claude Sonnet 4.5''' - Anthropic's general model
* '''Gemini-3 Flash''' - Google's fast model

'''Note''' - Models cannot be changed mid-conversation. Start a new chat to use a different model.

==== Menu items ====
* '''Account''' - View your profile and sign out
* '''Settings''' - Theme, colors, and custom instructions
* '''Insights''' - Editorial analytics dashboard
* '''Help''' - Link to documentation
* '''Sign Out''' - End your session

=== 3.3 Main Chat Window ===

==== Header ====
Shows the conversation title and current model badge.

==== Messages ====
* Your messages appear on the right
* Assistant messages appear on the left
* Hover over assistant messages to reveal the copy button

==== Message input ====
Type your message and press Enter or click Send.

== 4. Sending Messages ==

=== 4.1 Basic messaging ===
# Type your message in the input field
# Press '''Enter''' or click '''Send'''
# Wait for the assistant to respond

=== 4.2 Multi-line messages ===
Press '''Shift+Enter''' to create a new line without sending.

=== 4.3 Stop generation ===
While the assistant is responding, click '''Stop''' to halt generation early.

== 5. Options Menu ==

The '''Options''' button inside the message input area provides access to:
* File uploads
* Prompt templates
* Quick actions

=== 5.1 Opening Options ===
Click the '''Options''' button to reveal the dropdown menu.

== 6. File Uploads ==

=== 6.1 Upload a file ===
# Click '''Options'''
# Select '''Upload files'''
# Choose one or more files

=== 6.2 Supported file types ===
* '''Text:''' .txt, .md, .csv, .tsv, .json
* '''Documents:''' .pdf, .doc, .docx
* '''Presentations:''' .ppt, .pptx
* '''Spreadsheets:''' .xls, .xlsx
* '''Images:''' .png, .jpg, .gif, .webp, .bmp, .tiff

=== 6.3 File status ===
Uploaded files appear as chips above the input:
* '''Uploaded''' - File received
* '''Parsed''' - Text extracted and available to the model

=== 6.4 Remove a file ===
Click the '''×''' on the file chip to remove it from the conversation.

=== 6.5 File size limit ===
Maximum upload size is 25 MB per file.

== 7. Prompt Templates ==

Templates provide structured prompts for common content types.

=== 7.1 Using a template ===
# Click '''Options'''
# Select a template from the list
# The template badge appears above the input
# Type your specific content or context
# Send your message

=== 7.2 Available templates ===

==== Landing Pages ====
{| class="wikitable"
! Template !! Description
|-
| Locations || Global offices and delivery centers
|-
| Services || Service overview
|-
| Industries || Industry overview or specialization page
|-
| Leadership || Leadership team
|-
| Clients || Client portfolio
|}

==== Case Studies ====
{| class="wikitable"
! Template !! Description
|-
| Case Study (PPT) || PowerPoint, single-page case study
|-
| Case Study (Website) || SEO-optimized case study with KPIs
|}

=== 7.3 Template behavior ===
* Templates automatically use '''Google Gemini''' for optimal results
* The template badge shows which template is active
* Click '''×''' on the badge to clear the template

== 8. Quick Actions ==

Quick actions transform the previous AI response with one click.

=== 8.1 Available quick actions ===
{| class="wikitable"
! Action !! Effect
|-
| Make it shorter || Condense to ~50% of original length
|-
| Make it more formal || Increase professional tone
|-
| Simplify this || Make clearer and more accessible
|-
| Expand on this || Add detail and elaboration
|}

=== 8.2 Using quick actions ===
# You must write a prompt and receive a message before you can run a quick action
# Click '''Options'''
# Select a quick action
# The action executes using Gemini 3

== 9. Editorial Insights ==

The Insights dashboard shows a user's editorial analytics.

=== 9.1 Accessing Insights ===
# Open the sidebar
# Click '''Insights''' in the menu

=== 9.2 Metrics displayed ===
* '''Total Messages''' - Number of messages processed
* '''Passed''' - Messages without AI pattern violations
* '''Violations''' - Messages where patterns were detected and corrected
* '''Pass Rate''' - Percentage of clean messages

=== 9.3 Top Violations ===
Shows the most common AI-typical words detected in your conversations.

=== 9.4 Recent Corrections ===
Examples of recent messages where the editorial system improved the output.

== 10. Conversation Export ==

Export your conversations.

=== 10.1 Export formats ===
* '''Markdown''' - Formatted text file that can be rendered in a Markdown reader
* '''JSON''' - Structured data

=== 10.2 How to export ===
# Open the conversation you want to export
# Click the '''Export''' button in the header
# Select '''Markdown''' or '''JSON'''
# The file downloads automatically

== 11. Settings ==

=== 11.1 Theme ===
* '''Light''' - Light background
* '''Dark''' - Dark background
* '''System''' - Match your operating system preference

=== 11.2 Primary color ===
Choose an accent color for buttons and highlights.

=== 11.3 Custom instructions ===
Provide information about your personal preferences that the AI assistant should remember. This is information about the user that helps the AI write more personalized responses.

=== 11.4 LLM instructions ===
Add rules for how the AI assistant should respond

== 12. The Two-Pass Editorial System ==

Righting Sentences uses a unique two-pass system to improve AI output.

=== 12.1 How it works ===
# '''Pass 1:''' The AI generates a natural response
# '''Detection:''' The system identifies AI-typical patterns:
#* Banned words (e.g., "utilize", "landscape", "delve")
#* Three-part lists (triads)
#* Rhetorical patterns (e.g., "It's not X, it's Y")
# '''Pass 2:''' The AI regenerates with stricter guidelines
# '''Post-processing:''' Any remaining issues are cleaned programmatically

=== 12.2 Why it matters ===
AI models tend to overuse certain words and patterns that make text sound artificial. The editorial system produces writing that sounds more natural and human-like.

=== 12.3 Banned words ===
The system currently flags: utilize, landscape, unlock, critical, guardrails, tracks, shape, shift, teams, delve, tapestry.

=== 12.4 Triad exceptions ===
Some three-part phrases are culturally significant and exempt from editing:
* "executive, legislative, and judicial"
* "life, liberty, and the pursuit of happiness"
* "red, white, and blue"

== 13. Troubleshooting ==

=== 13.1 I cannot sign in ===
* Confirm you are using a Google account
* Confirm your account has been invited
* Contact Saxton Publishing if the problem persists

=== 13.2 I cannot change the model ===
Models cannot be changed mid-conversation. Start a new chat to use a different model.

=== 13.3 Quick actions are not available ===
Quick actions require at least one assistant message in the conversation. Send a message first, then use quick actions.

=== 13.4 Template is not working ===
* Ensure the template badge is visible above the input
* Templates require you to provide context in your message
* If issues persist, clear the template and try again

=== 13.5 File upload fails ===
* Check that the file is under 25 MB
* Verify the file type is supported
* Contact the administrator if errors persist

== 14. Data and Privacy ==

=== 14.1 What is stored ===
* Conversations and messages
* Uploaded files
* Editorial logs (for system improvement)

=== 14.2 Where data is stored ===
* Google Cloud Firestore (conversations, metadata)
* Google Cloud Storage (uploaded files)

=== 14.3 Third-party providers ===
Messages are sent to the selected model provider (OpenAI, Anthropic, or Google) to generate responses.

----
''Righting Sentences is developed by Saxton Publishing.''

[[Category:Righting Sentences]]
[[Category:User Guide]]

Righting Sentences User Guide - 4.0

2026-02-07T00:08:36Z

Saxtonmd77: /* 11.4 LLM instructions */

'''Righting Sentences''' — User Guide (v4.0)

Last updated: February 2026

Production URL: https://righting-sentences-573737403792.us-east1.run.app/

__TOC__

== 1. Purpose and Scope ==
Righting Sentences is a web-based chat application that generates AI text that reads more like standard written English. This application is a data science project that includes a unique two-pass editorial system, the Morey Language Model which automatically detects and removes AI-typical language patterns. Usage improves the Morey Language Model, an editorial system that eventually will include a fine-tuned foundational LLM.

== 2. Access and Authentication ==

=== 2.1 Google account required ===
To use the application, you must sign in with a Google account.

=== 2.2 Invitation-only access ===
Access is provided by invitation. If you cannot sign in or do not see the application after signing in, contact the administrator at https://saxtonpublishing.com/contact/.

=== 2.3 Sign in ===
# Navigate to the production URL
# Select '''Sign in with Google'''
# Complete Google authentication
# After sign-in, you will see the main chat interface

== 3. User Interface ==

=== 3.1 Layout overview ===
The interface has two main areas:
* '''Left sidebar''' - Chat history, model selector, and menu
* '''Main chat window''' - Conversation view and message input

=== 3.2 Left Sidebar ===

==== Chat history list ====
Each row shows:
* The conversation title
* The model used for that conversation

To open a conversation, select it from the list.

==== Model selector ====
Choose which AI model to use for new conversations:
* '''GPT-4o''' - OpenAI's most famous model
* '''GPT-5.2 Pro''' - OpenAI's advanced reasoning model
* '''Claude Sonnet 4.5''' - Anthropic's general model
* '''Gemini-3 Flash''' - Google's fast model

'''Note''' - Models cannot be changed mid-conversation. Start a new chat to use a different model.

==== Menu items ====
* '''Account''' - View your profile and sign out
* '''Settings''' - Theme, colors, and custom instructions
* '''Insights''' - Editorial analytics dashboard
* '''Help''' - Link to documentation
* '''Sign Out''' - End your session

=== 3.3 Main Chat Window ===

==== Header ====
Shows the conversation title and current model badge.

==== Messages ====
* Your messages appear on the right
* Assistant messages appear on the left
* Hover over assistant messages to reveal the copy button

==== Message input ====
Type your message and press Enter or click Send.

== 4. Sending Messages ==

=== 4.1 Basic messaging ===
# Type your message in the input field
# Press '''Enter''' or click '''Send'''
# Wait for the assistant to respond

=== 4.2 Multi-line messages ===
Press '''Shift+Enter''' to create a new line without sending.

=== 4.3 Stop generation ===
While the assistant is responding, click '''Stop''' to halt generation early.

== 5. Options Menu ==

The '''Options''' button inside the message input area provides access to:
* File uploads
* Prompt templates
* Quick actions

=== 5.1 Opening Options ===
Click the '''Options''' button to reveal the dropdown menu.

== 6. File Uploads ==

=== 6.1 Upload a file ===
# Click '''Options'''
# Select '''Upload files'''
# Choose one or more files

=== 6.2 Supported file types ===
* '''Text:''' .txt, .md, .csv, .tsv, .json
* '''Documents:''' .pdf, .doc, .docx
* '''Presentations:''' .ppt, .pptx
* '''Spreadsheets:''' .xls, .xlsx
* '''Images:''' .png, .jpg, .gif, .webp, .bmp, .tiff

=== 6.3 File status ===
Uploaded files appear as chips above the input:
* '''Uploaded''' - File received
* '''Parsed''' - Text extracted and available to the model

=== 6.4 Remove a file ===
Click the '''×''' on the file chip to remove it from the conversation.

=== 6.5 File size limit ===
Maximum upload size is 25 MB per file.

== 7. Prompt Templates ==

Templates provide structured prompts for common content types.

=== 7.1 Using a template ===
# Click '''Options'''
# Select a template from the list
# The template badge appears above the input
# Type your specific content or context
# Send your message

=== 7.2 Available templates ===

==== Landing Pages ====
{| class="wikitable"
! Template !! Description
|-
| Locations || Global offices and delivery centers
|-
| Services || Service overview
|-
| Industries || Industry overview or specialization page
|-
| Leadership || Leadership team
|-
| Clients || Client portfolio
|}

==== Case Studies ====
{| class="wikitable"
! Template !! Description
|-
| Case Study (PPT) || PowerPoint, single-page case study
|-
| Case Study (Website) || SEO-optimized case study with KPIs
|}

=== 7.3 Template behavior ===
* Templates automatically use '''Google Gemini''' for optimal results
* The template badge shows which template is active
* Click '''×''' on the badge to clear the template

== 8. Quick Actions ==

Quick actions transform the previous AI response with one click.

=== 8.1 Available quick actions ===
{| class="wikitable"
! Action !! Effect
|-
| Make it shorter || Condense to ~50% of original length
|-
| Make it more formal || Increase professional tone
|-
| Simplify this || Make clearer and more accessible
|-
| Expand on this || Add detail and elaboration
|}

=== 8.2 Using quick actions ===
# You must write a prompt and receive a message before you can run a quick action
# Click '''Options'''
# Select a quick action
# The action executes using Gemini 3

== 9. Editorial Insights ==

The Insights dashboard shows a user's editorial analytics.

=== 9.1 Accessing Insights ===
# Open the sidebar
# Click '''Insights''' in the menu

=== 9.2 Metrics displayed ===
* '''Total Messages''' - Number of messages processed
* '''Passed''' - Messages without AI pattern violations
* '''Violations''' - Messages where patterns were detected and corrected
* '''Pass Rate''' - Percentage of clean messages

=== 9.3 Top Violations ===
Shows the most common AI-typical words detected in your conversations.

=== 9.4 Recent Corrections ===
Examples of recent messages where the editorial system improved the output.

== 10. Conversation Export ==

Export your conversations.

=== 10.1 Export formats ===
* '''Markdown''' - Formatted text file that can be rendered in a Markdown reader
* '''JSON''' - Structured data

=== 10.2 How to export ===
# Open the conversation you want to export
# Click the '''Export''' button in the header
# Select '''Markdown''' or '''JSON'''
# The file downloads automatically

== 11. Settings ==

=== 11.1 Theme ===
* '''Light''' - Light background
* '''Dark''' - Dark background
* '''System''' - Match your operating system preference

=== 11.2 Primary color ===
Choose an accent color for buttons and highlights.

=== 11.3 Custom instructions ===
Provide information about your preferences that the AI assistant should remember.

=== 11.4 LLM instructions ===
Add rules for how the AI assistant should respond

== 12. The Two-Pass Editorial System ==

Righting Sentences uses a unique two-pass system to improve AI output.

=== 12.1 How it works ===
# '''Pass 1:''' The AI generates a natural response
# '''Detection:''' The system identifies AI-typical patterns:
#* Banned words (e.g., "utilize", "landscape", "delve")
#* Three-part lists (triads)
#* Rhetorical patterns (e.g., "It's not X, it's Y")
# '''Pass 2:''' The AI regenerates with stricter guidelines
# '''Post-processing:''' Any remaining issues are cleaned programmatically

=== 12.2 Why it matters ===
AI models tend to overuse certain words and patterns that make text sound artificial. The editorial system produces writing that sounds more natural and human-like.

=== 12.3 Banned words ===
The system currently flags: utilize, landscape, unlock, critical, guardrails, tracks, shape, shift, teams, delve, tapestry.

=== 12.4 Triad exceptions ===
Some three-part phrases are culturally significant and exempt from editing:
* "executive, legislative, and judicial"
* "life, liberty, and the pursuit of happiness"
* "red, white, and blue"

== 13. Troubleshooting ==

=== 13.1 I cannot sign in ===
* Confirm you are using a Google account
* Confirm your account has been invited
* Contact Saxton Publishing if the problem persists

=== 13.2 I cannot change the model ===
Models cannot be changed mid-conversation. Start a new chat to use a different model.

=== 13.3 Quick actions are not available ===
Quick actions require at least one assistant message in the conversation. Send a message first, then use quick actions.

=== 13.4 Template is not working ===
* Ensure the template badge is visible above the input
* Templates require you to provide context in your message
* If issues persist, clear the template and try again

=== 13.5 File upload fails ===
* Check that the file is under 25 MB
* Verify the file type is supported
* Contact the administrator if errors persist

== 14. Data and Privacy ==

=== 14.1 What is stored ===
* Conversations and messages
* Uploaded files
* Editorial logs (for system improvement)

=== 14.2 Where data is stored ===
* Google Cloud Firestore (conversations, metadata)
* Google Cloud Storage (uploaded files)

=== 14.3 Third-party providers ===
Messages are sent to the selected model provider (OpenAI, Anthropic, or Google) to generate responses.

----
''Righting Sentences is developed by Saxton Publishing.''

[[Category:Righting Sentences]]
[[Category:User Guide]]

Righting Sentences User Guide - 4.0

2026-02-07T00:08:17Z

Saxtonmd77: /* 11.3 Custom instructions */

'''Righting Sentences''' — User Guide (v4.0)

Last updated: February 2026

Production URL: https://righting-sentences-573737403792.us-east1.run.app/

__TOC__

== 1. Purpose and Scope ==
Righting Sentences is a web-based chat application that generates AI text that reads more like standard written English. This application is a data science project that includes a unique two-pass editorial system, the Morey Language Model which automatically detects and removes AI-typical language patterns. Usage improves the Morey Language Model, an editorial system that eventually will include a fine-tuned foundational LLM.

== 2. Access and Authentication ==

=== 2.1 Google account required ===
To use the application, you must sign in with a Google account.

=== 2.2 Invitation-only access ===
Access is provided by invitation. If you cannot sign in or do not see the application after signing in, contact the administrator at https://saxtonpublishing.com/contact/.

=== 2.3 Sign in ===
# Navigate to the production URL
# Select '''Sign in with Google'''
# Complete Google authentication
# After sign-in, you will see the main chat interface

== 3. User Interface ==

=== 3.1 Layout overview ===
The interface has two main areas:
* '''Left sidebar''' - Chat history, model selector, and menu
* '''Main chat window''' - Conversation view and message input

=== 3.2 Left Sidebar ===

==== Chat history list ====
Each row shows:
* The conversation title
* The model used for that conversation

To open a conversation, select it from the list.

==== Model selector ====
Choose which AI model to use for new conversations:
* '''GPT-4o''' - OpenAI's most famous model
* '''GPT-5.2 Pro''' - OpenAI's advanced reasoning model
* '''Claude Sonnet 4.5''' - Anthropic's general model
* '''Gemini-3 Flash''' - Google's fast model

'''Note''' - Models cannot be changed mid-conversation. Start a new chat to use a different model.

==== Menu items ====
* '''Account''' - View your profile and sign out
* '''Settings''' - Theme, colors, and custom instructions
* '''Insights''' - Editorial analytics dashboard
* '''Help''' - Link to documentation
* '''Sign Out''' - End your session

=== 3.3 Main Chat Window ===

==== Header ====
Shows the conversation title and current model badge.

==== Messages ====
* Your messages appear on the right
* Assistant messages appear on the left
* Hover over assistant messages to reveal the copy button

==== Message input ====
Type your message and press Enter or click Send.

== 4. Sending Messages ==

=== 4.1 Basic messaging ===
# Type your message in the input field
# Press '''Enter''' or click '''Send'''
# Wait for the assistant to respond

=== 4.2 Multi-line messages ===
Press '''Shift+Enter''' to create a new line without sending.

=== 4.3 Stop generation ===
While the assistant is responding, click '''Stop''' to halt generation early.

== 5. Options Menu ==

The '''Options''' button inside the message input area provides access to:
* File uploads
* Prompt templates
* Quick actions

=== 5.1 Opening Options ===
Click the '''Options''' button to reveal the dropdown menu.

== 6. File Uploads ==

=== 6.1 Upload a file ===
# Click '''Options'''
# Select '''Upload files'''
# Choose one or more files

=== 6.2 Supported file types ===
* '''Text:''' .txt, .md, .csv, .tsv, .json
* '''Documents:''' .pdf, .doc, .docx
* '''Presentations:''' .ppt, .pptx
* '''Spreadsheets:''' .xls, .xlsx
* '''Images:''' .png, .jpg, .gif, .webp, .bmp, .tiff

=== 6.3 File status ===
Uploaded files appear as chips above the input:
* '''Uploaded''' - File received
* '''Parsed''' - Text extracted and available to the model

=== 6.4 Remove a file ===
Click the '''×''' on the file chip to remove it from the conversation.

=== 6.5 File size limit ===
Maximum upload size is 25 MB per file.

== 7. Prompt Templates ==

Templates provide structured prompts for common content types.

=== 7.1 Using a template ===
# Click '''Options'''
# Select a template from the list
# The template badge appears above the input
# Type your specific content or context
# Send your message

=== 7.2 Available templates ===

==== Landing Pages ====
{| class="wikitable"
! Template !! Description
|-
| Locations || Global offices and delivery centers
|-
| Services || Service overview
|-
| Industries || Industry overview or specialization page
|-
| Leadership || Leadership team
|-
| Clients || Client portfolio
|}

==== Case Studies ====
{| class="wikitable"
! Template !! Description
|-
| Case Study (PPT) || PowerPoint, single-page case study
|-
| Case Study (Website) || SEO-optimized case study with KPIs
|}

=== 7.3 Template behavior ===
* Templates automatically use '''Google Gemini''' for optimal results
* The template badge shows which template is active
* Click '''×''' on the badge to clear the template

== 8. Quick Actions ==

Quick actions transform the previous AI response with one click.

=== 8.1 Available quick actions ===
{| class="wikitable"
! Action !! Effect
|-
| Make it shorter || Condense to ~50% of original length
|-
| Make it more formal || Increase professional tone
|-
| Simplify this || Make clearer and more accessible
|-
| Expand on this || Add detail and elaboration
|}

=== 8.2 Using quick actions ===
# You must write a prompt and receive a message before you can run a quick action
# Click '''Options'''
# Select a quick action
# The action executes using Gemini 3

== 9. Editorial Insights ==

The Insights dashboard shows a user's editorial analytics.

=== 9.1 Accessing Insights ===
# Open the sidebar
# Click '''Insights''' in the menu

=== 9.2 Metrics displayed ===
* '''Total Messages''' - Number of messages processed
* '''Passed''' - Messages without AI pattern violations
* '''Violations''' - Messages where patterns were detected and corrected
* '''Pass Rate''' - Percentage of clean messages

=== 9.3 Top Violations ===
Shows the most common AI-typical words detected in your conversations.

=== 9.4 Recent Corrections ===
Examples of recent messages where the editorial system improved the output.

== 10. Conversation Export ==

Export your conversations.

=== 10.1 Export formats ===
* '''Markdown''' - Formatted text file that can be rendered in a Markdown reader
* '''JSON''' - Structured data

=== 10.2 How to export ===
# Open the conversation you want to export
# Click the '''Export''' button in the header
# Select '''Markdown''' or '''JSON'''
# The file downloads automatically

== 11. Settings ==

=== 11.1 Theme ===
* '''Light''' - Light background
* '''Dark''' - Dark background
* '''System''' - Match your operating system preference

=== 11.2 Primary color ===
Choose an accent color for buttons and highlights.

=== 11.3 Custom instructions ===
Provide information about your preferences that the AI assistant should remember.

=== 11.4 LLM instructions ===
Add rules for how the assistant should respond in all conversations.

== 12. The Two-Pass Editorial System ==

Righting Sentences uses a unique two-pass system to improve AI output.

=== 12.1 How it works ===
# '''Pass 1:''' The AI generates a natural response
# '''Detection:''' The system identifies AI-typical patterns:
#* Banned words (e.g., "utilize", "landscape", "delve")
#* Three-part lists (triads)
#* Rhetorical patterns (e.g., "It's not X, it's Y")
# '''Pass 2:''' The AI regenerates with stricter guidelines
# '''Post-processing:''' Any remaining issues are cleaned programmatically

=== 12.2 Why it matters ===
AI models tend to overuse certain words and patterns that make text sound artificial. The editorial system produces writing that sounds more natural and human-like.

=== 12.3 Banned words ===
The system currently flags: utilize, landscape, unlock, critical, guardrails, tracks, shape, shift, teams, delve, tapestry.

=== 12.4 Triad exceptions ===
Some three-part phrases are culturally significant and exempt from editing:
* "executive, legislative, and judicial"
* "life, liberty, and the pursuit of happiness"
* "red, white, and blue"

== 13. Troubleshooting ==

=== 13.1 I cannot sign in ===
* Confirm you are using a Google account
* Confirm your account has been invited
* Contact Saxton Publishing if the problem persists

=== 13.2 I cannot change the model ===
Models cannot be changed mid-conversation. Start a new chat to use a different model.

=== 13.3 Quick actions are not available ===
Quick actions require at least one assistant message in the conversation. Send a message first, then use quick actions.

=== 13.4 Template is not working ===
* Ensure the template badge is visible above the input
* Templates require you to provide context in your message
* If issues persist, clear the template and try again

=== 13.5 File upload fails ===
* Check that the file is under 25 MB
* Verify the file type is supported
* Contact the administrator if errors persist

== 14. Data and Privacy ==

=== 14.1 What is stored ===
* Conversations and messages
* Uploaded files
* Editorial logs (for system improvement)

=== 14.2 Where data is stored ===
* Google Cloud Firestore (conversations, metadata)
* Google Cloud Storage (uploaded files)

=== 14.3 Third-party providers ===
Messages are sent to the selected model provider (OpenAI, Anthropic, or Google) to generate responses.

----
''Righting Sentences is developed by Saxton Publishing.''

[[Category:Righting Sentences]]
[[Category:User Guide]]

Righting Sentences User Guide - 4.0

2026-02-07T00:07:13Z

Saxtonmd77: /* 10. Conversation Export */

'''Righting Sentences''' — User Guide (v4.0)

Last updated: February 2026

Production URL: https://righting-sentences-573737403792.us-east1.run.app/

__TOC__

== 1. Purpose and Scope ==
Righting Sentences is a web-based chat application that generates AI text that reads more like standard written English. This application is a data science project that includes a unique two-pass editorial system, the Morey Language Model which automatically detects and removes AI-typical language patterns. Usage improves the Morey Language Model, an editorial system that eventually will include a fine-tuned foundational LLM.

== 2. Access and Authentication ==

=== 2.1 Google account required ===
To use the application, you must sign in with a Google account.

=== 2.2 Invitation-only access ===
Access is provided by invitation. If you cannot sign in or do not see the application after signing in, contact the administrator at https://saxtonpublishing.com/contact/.

=== 2.3 Sign in ===
# Navigate to the production URL
# Select '''Sign in with Google'''
# Complete Google authentication
# After sign-in, you will see the main chat interface

== 3. User Interface ==

=== 3.1 Layout overview ===
The interface has two main areas:
* '''Left sidebar''' - Chat history, model selector, and menu
* '''Main chat window''' - Conversation view and message input

=== 3.2 Left Sidebar ===

==== Chat history list ====
Each row shows:
* The conversation title
* The model used for that conversation

To open a conversation, select it from the list.

==== Model selector ====
Choose which AI model to use for new conversations:
* '''GPT-4o''' - OpenAI's most famous model
* '''GPT-5.2 Pro''' - OpenAI's advanced reasoning model
* '''Claude Sonnet 4.5''' - Anthropic's general model
* '''Gemini-3 Flash''' - Google's fast model

'''Note''' - Models cannot be changed mid-conversation. Start a new chat to use a different model.

==== Menu items ====
* '''Account''' - View your profile and sign out
* '''Settings''' - Theme, colors, and custom instructions
* '''Insights''' - Editorial analytics dashboard
* '''Help''' - Link to documentation
* '''Sign Out''' - End your session

=== 3.3 Main Chat Window ===

==== Header ====
Shows the conversation title and current model badge.

==== Messages ====
* Your messages appear on the right
* Assistant messages appear on the left
* Hover over assistant messages to reveal the copy button

==== Message input ====
Type your message and press Enter or click Send.

== 4. Sending Messages ==

=== 4.1 Basic messaging ===
# Type your message in the input field
# Press '''Enter''' or click '''Send'''
# Wait for the assistant to respond

=== 4.2 Multi-line messages ===
Press '''Shift+Enter''' to create a new line without sending.

=== 4.3 Stop generation ===
While the assistant is responding, click '''Stop''' to halt generation early.

== 5. Options Menu ==

The '''Options''' button inside the message input area provides access to:
* File uploads
* Prompt templates
* Quick actions

=== 5.1 Opening Options ===
Click the '''Options''' button to reveal the dropdown menu.

== 6. File Uploads ==

=== 6.1 Upload a file ===
# Click '''Options'''
# Select '''Upload files'''
# Choose one or more files

=== 6.2 Supported file types ===
* '''Text:''' .txt, .md, .csv, .tsv, .json
* '''Documents:''' .pdf, .doc, .docx
* '''Presentations:''' .ppt, .pptx
* '''Spreadsheets:''' .xls, .xlsx
* '''Images:''' .png, .jpg, .gif, .webp, .bmp, .tiff

=== 6.3 File status ===
Uploaded files appear as chips above the input:
* '''Uploaded''' - File received
* '''Parsed''' - Text extracted and available to the model

=== 6.4 Remove a file ===
Click the '''×''' on the file chip to remove it from the conversation.

=== 6.5 File size limit ===
Maximum upload size is 25 MB per file.

== 7. Prompt Templates ==

Templates provide structured prompts for common content types.

=== 7.1 Using a template ===
# Click '''Options'''
# Select a template from the list
# The template badge appears above the input
# Type your specific content or context
# Send your message

=== 7.2 Available templates ===

==== Landing Pages ====
{| class="wikitable"
! Template !! Description
|-
| Locations || Global offices and delivery centers
|-
| Services || Service overview
|-
| Industries || Industry overview or specialization page
|-
| Leadership || Leadership team
|-
| Clients || Client portfolio
|}

==== Case Studies ====
{| class="wikitable"
! Template !! Description
|-
| Case Study (PPT) || PowerPoint, single-page case study
|-
| Case Study (Website) || SEO-optimized case study with KPIs
|}

=== 7.3 Template behavior ===
* Templates automatically use '''Google Gemini''' for optimal results
* The template badge shows which template is active
* Click '''×''' on the badge to clear the template

== 8. Quick Actions ==

Quick actions transform the previous AI response with one click.

=== 8.1 Available quick actions ===
{| class="wikitable"
! Action !! Effect
|-
| Make it shorter || Condense to ~50% of original length
|-
| Make it more formal || Increase professional tone
|-
| Simplify this || Make clearer and more accessible
|-
| Expand on this || Add detail and elaboration
|}

=== 8.2 Using quick actions ===
# You must write a prompt and receive a message before you can run a quick action
# Click '''Options'''
# Select a quick action
# The action executes using Gemini 3

== 9. Editorial Insights ==

The Insights dashboard shows a user's editorial analytics.

=== 9.1 Accessing Insights ===
# Open the sidebar
# Click '''Insights''' in the menu

=== 9.2 Metrics displayed ===
* '''Total Messages''' - Number of messages processed
* '''Passed''' - Messages without AI pattern violations
* '''Violations''' - Messages where patterns were detected and corrected
* '''Pass Rate''' - Percentage of clean messages

=== 9.3 Top Violations ===
Shows the most common AI-typical words detected in your conversations.

=== 9.4 Recent Corrections ===
Examples of recent messages where the editorial system improved the output.

== 10. Conversation Export ==

Export your conversations.

=== 10.1 Export formats ===
* '''Markdown''' - Formatted text file that can be rendered in a Markdown reader
* '''JSON''' - Structured data

=== 10.2 How to export ===
# Open the conversation you want to export
# Click the '''Export''' button in the header
# Select '''Markdown''' or '''JSON'''
# The file downloads automatically

== 11. Settings ==

=== 11.1 Theme ===
* '''Light''' - Light background
* '''Dark''' - Dark background
* '''System''' - Match your operating system preference

=== 11.2 Primary color ===
Choose an accent color for buttons and highlights.

=== 11.3 Custom instructions ===
Provide information about your preferences that the assistant should remember.

=== 11.4 LLM instructions ===
Add rules for how the assistant should respond in all conversations.

== 12. The Two-Pass Editorial System ==

Righting Sentences uses a unique two-pass system to improve AI output.

=== 12.1 How it works ===
# '''Pass 1:''' The AI generates a natural response
# '''Detection:''' The system identifies AI-typical patterns:
#* Banned words (e.g., "utilize", "landscape", "delve")
#* Three-part lists (triads)
#* Rhetorical patterns (e.g., "It's not X, it's Y")
# '''Pass 2:''' The AI regenerates with stricter guidelines
# '''Post-processing:''' Any remaining issues are cleaned programmatically

=== 12.2 Why it matters ===
AI models tend to overuse certain words and patterns that make text sound artificial. The editorial system produces writing that sounds more natural and human-like.

=== 12.3 Banned words ===
The system currently flags: utilize, landscape, unlock, critical, guardrails, tracks, shape, shift, teams, delve, tapestry.

=== 12.4 Triad exceptions ===
Some three-part phrases are culturally significant and exempt from editing:
* "executive, legislative, and judicial"
* "life, liberty, and the pursuit of happiness"
* "red, white, and blue"

== 13. Troubleshooting ==

=== 13.1 I cannot sign in ===
* Confirm you are using a Google account
* Confirm your account has been invited
* Contact Saxton Publishing if the problem persists

=== 13.2 I cannot change the model ===
Models cannot be changed mid-conversation. Start a new chat to use a different model.

=== 13.3 Quick actions are not available ===
Quick actions require at least one assistant message in the conversation. Send a message first, then use quick actions.

=== 13.4 Template is not working ===
* Ensure the template badge is visible above the input
* Templates require you to provide context in your message
* If issues persist, clear the template and try again

=== 13.5 File upload fails ===
* Check that the file is under 25 MB
* Verify the file type is supported
* Contact the administrator if errors persist

== 14. Data and Privacy ==

=== 14.1 What is stored ===
* Conversations and messages
* Uploaded files
* Editorial logs (for system improvement)

=== 14.2 Where data is stored ===
* Google Cloud Firestore (conversations, metadata)
* Google Cloud Storage (uploaded files)

=== 14.3 Third-party providers ===
Messages are sent to the selected model provider (OpenAI, Anthropic, or Google) to generate responses.

----
''Righting Sentences is developed by Saxton Publishing.''

[[Category:Righting Sentences]]
[[Category:User Guide]]

Righting Sentences User Guide - 4.0

2026-02-07T00:06:19Z

Saxtonmd77: /* 9. Editorial Insights */

'''Righting Sentences''' — User Guide (v4.0)

Last updated: February 2026

Production URL: https://righting-sentences-573737403792.us-east1.run.app/

__TOC__

== 1. Purpose and Scope ==
Righting Sentences is a web-based chat application that generates AI text that reads more like standard written English. This application is a data science project that includes a unique two-pass editorial system, the Morey Language Model which automatically detects and removes AI-typical language patterns. Usage improves the Morey Language Model, an editorial system that eventually will include a fine-tuned foundational LLM.

== 2. Access and Authentication ==

=== 2.1 Google account required ===
To use the application, you must sign in with a Google account.

=== 2.2 Invitation-only access ===
Access is provided by invitation. If you cannot sign in or do not see the application after signing in, contact the administrator at https://saxtonpublishing.com/contact/.

=== 2.3 Sign in ===
# Navigate to the production URL
# Select '''Sign in with Google'''
# Complete Google authentication
# After sign-in, you will see the main chat interface

== 3. User Interface ==

=== 3.1 Layout overview ===
The interface has two main areas:
* '''Left sidebar''' - Chat history, model selector, and menu
* '''Main chat window''' - Conversation view and message input

=== 3.2 Left Sidebar ===

==== Chat history list ====
Each row shows:
* The conversation title
* The model used for that conversation

To open a conversation, select it from the list.

==== Model selector ====
Choose which AI model to use for new conversations:
* '''GPT-4o''' - OpenAI's most famous model
* '''GPT-5.2 Pro''' - OpenAI's advanced reasoning model
* '''Claude Sonnet 4.5''' - Anthropic's general model
* '''Gemini-3 Flash''' - Google's fast model

'''Note''' - Models cannot be changed mid-conversation. Start a new chat to use a different model.

==== Menu items ====
* '''Account''' - View your profile and sign out
* '''Settings''' - Theme, colors, and custom instructions
* '''Insights''' - Editorial analytics dashboard
* '''Help''' - Link to documentation
* '''Sign Out''' - End your session

=== 3.3 Main Chat Window ===

==== Header ====
Shows the conversation title and current model badge.

==== Messages ====
* Your messages appear on the right
* Assistant messages appear on the left
* Hover over assistant messages to reveal the copy button

==== Message input ====
Type your message and press Enter or click Send.

== 4. Sending Messages ==

=== 4.1 Basic messaging ===
# Type your message in the input field
# Press '''Enter''' or click '''Send'''
# Wait for the assistant to respond

=== 4.2 Multi-line messages ===
Press '''Shift+Enter''' to create a new line without sending.

=== 4.3 Stop generation ===
While the assistant is responding, click '''Stop''' to halt generation early.

== 5. Options Menu ==

The '''Options''' button inside the message input area provides access to:
* File uploads
* Prompt templates
* Quick actions

=== 5.1 Opening Options ===
Click the '''Options''' button to reveal the dropdown menu.

== 6. File Uploads ==

=== 6.1 Upload a file ===
# Click '''Options'''
# Select '''Upload files'''
# Choose one or more files

=== 6.2 Supported file types ===
* '''Text:''' .txt, .md, .csv, .tsv, .json
* '''Documents:''' .pdf, .doc, .docx
* '''Presentations:''' .ppt, .pptx
* '''Spreadsheets:''' .xls, .xlsx
* '''Images:''' .png, .jpg, .gif, .webp, .bmp, .tiff

=== 6.3 File status ===
Uploaded files appear as chips above the input:
* '''Uploaded''' - File received
* '''Parsed''' - Text extracted and available to the model

=== 6.4 Remove a file ===
Click the '''×''' on the file chip to remove it from the conversation.

=== 6.5 File size limit ===
Maximum upload size is 25 MB per file.

== 7. Prompt Templates ==

Templates provide structured prompts for common content types.

=== 7.1 Using a template ===
# Click '''Options'''
# Select a template from the list
# The template badge appears above the input
# Type your specific content or context
# Send your message

=== 7.2 Available templates ===

==== Landing Pages ====
{| class="wikitable"
! Template !! Description
|-
| Locations || Global offices and delivery centers
|-
| Services || Service overview
|-
| Industries || Industry overview or specialization page
|-
| Leadership || Leadership team
|-
| Clients || Client portfolio
|}

==== Case Studies ====
{| class="wikitable"
! Template !! Description
|-
| Case Study (PPT) || PowerPoint, single-page case study
|-
| Case Study (Website) || SEO-optimized case study with KPIs
|}

=== 7.3 Template behavior ===
* Templates automatically use '''Google Gemini''' for optimal results
* The template badge shows which template is active
* Click '''×''' on the badge to clear the template

== 8. Quick Actions ==

Quick actions transform the previous AI response with one click.

=== 8.1 Available quick actions ===
{| class="wikitable"
! Action !! Effect
|-
| Make it shorter || Condense to ~50% of original length
|-
| Make it more formal || Increase professional tone
|-
| Simplify this || Make clearer and more accessible
|-
| Expand on this || Add detail and elaboration
|}

=== 8.2 Using quick actions ===
# You must write a prompt and receive a message before you can run a quick action
# Click '''Options'''
# Select a quick action
# The action executes using Gemini 3

== 9. Editorial Insights ==

The Insights dashboard shows a user's editorial analytics.

=== 9.1 Accessing Insights ===
# Open the sidebar
# Click '''Insights''' in the menu

=== 9.2 Metrics displayed ===
* '''Total Messages''' - Number of messages processed
* '''Passed''' - Messages without AI pattern violations
* '''Violations''' - Messages where patterns were detected and corrected
* '''Pass Rate''' - Percentage of clean messages

=== 9.3 Top Violations ===
Shows the most common AI-typical words detected in your conversations.

=== 9.4 Recent Corrections ===
Examples of recent messages where the editorial system improved the output.

== 10. Conversation Export ==

Export your conversations for documentation or backup.

=== 10.1 Export formats ===
* '''Markdown''' - Formatted text file
* '''JSON''' - Structured data

=== 10.2 How to export ===
# Open the conversation you want to export
# Click the '''Export''' button in the header
# Select '''Markdown''' or '''JSON'''
# The file downloads automatically

== 11. Settings ==

=== 11.1 Theme ===
* '''Light''' - Light background
* '''Dark''' - Dark background
* '''System''' - Match your operating system preference

=== 11.2 Primary color ===
Choose an accent color for buttons and highlights.

=== 11.3 Custom instructions ===
Provide information about your preferences that the assistant should remember.

=== 11.4 LLM instructions ===
Add rules for how the assistant should respond in all conversations.

== 12. The Two-Pass Editorial System ==

Righting Sentences uses a unique two-pass system to improve AI output.

=== 12.1 How it works ===
# '''Pass 1:''' The AI generates a natural response
# '''Detection:''' The system identifies AI-typical patterns:
#* Banned words (e.g., "utilize", "landscape", "delve")
#* Three-part lists (triads)
#* Rhetorical patterns (e.g., "It's not X, it's Y")
# '''Pass 2:''' The AI regenerates with stricter guidelines
# '''Post-processing:''' Any remaining issues are cleaned programmatically

=== 12.2 Why it matters ===
AI models tend to overuse certain words and patterns that make text sound artificial. The editorial system produces writing that sounds more natural and human-like.

=== 12.3 Banned words ===
The system currently flags: utilize, landscape, unlock, critical, guardrails, tracks, shape, shift, teams, delve, tapestry.

=== 12.4 Triad exceptions ===
Some three-part phrases are culturally significant and exempt from editing:
* "executive, legislative, and judicial"
* "life, liberty, and the pursuit of happiness"
* "red, white, and blue"

== 13. Troubleshooting ==

=== 13.1 I cannot sign in ===
* Confirm you are using a Google account
* Confirm your account has been invited
* Contact Saxton Publishing if the problem persists

=== 13.2 I cannot change the model ===
Models cannot be changed mid-conversation. Start a new chat to use a different model.

=== 13.3 Quick actions are not available ===
Quick actions require at least one assistant message in the conversation. Send a message first, then use quick actions.

=== 13.4 Template is not working ===
* Ensure the template badge is visible above the input
* Templates require you to provide context in your message
* If issues persist, clear the template and try again

=== 13.5 File upload fails ===
* Check that the file is under 25 MB
* Verify the file type is supported
* Contact the administrator if errors persist

== 14. Data and Privacy ==

=== 14.1 What is stored ===
* Conversations and messages
* Uploaded files
* Editorial logs (for system improvement)

=== 14.2 Where data is stored ===
* Google Cloud Firestore (conversations, metadata)
* Google Cloud Storage (uploaded files)

=== 14.3 Third-party providers ===
Messages are sent to the selected model provider (OpenAI, Anthropic, or Google) to generate responses.

----
''Righting Sentences is developed by Saxton Publishing.''

[[Category:Righting Sentences]]
[[Category:User Guide]]

Righting Sentences User Guide - 4.0

2026-02-07T00:05:29Z

Saxtonmd77: /* 8.3 Quick action behavior */

'''Righting Sentences''' — User Guide (v4.0)

Last updated: February 2026

Production URL: https://righting-sentences-573737403792.us-east1.run.app/

__TOC__

== 1. Purpose and Scope ==
Righting Sentences is a web-based chat application that generates AI text that reads more like standard written English. This application is a data science project that includes a unique two-pass editorial system, the Morey Language Model which automatically detects and removes AI-typical language patterns. Usage improves the Morey Language Model, an editorial system that eventually will include a fine-tuned foundational LLM.

== 2. Access and Authentication ==

=== 2.1 Google account required ===
To use the application, you must sign in with a Google account.

=== 2.2 Invitation-only access ===
Access is provided by invitation. If you cannot sign in or do not see the application after signing in, contact the administrator at https://saxtonpublishing.com/contact/.

=== 2.3 Sign in ===
# Navigate to the production URL
# Select '''Sign in with Google'''
# Complete Google authentication
# After sign-in, you will see the main chat interface

== 3. User Interface ==

=== 3.1 Layout overview ===
The interface has two main areas:
* '''Left sidebar''' - Chat history, model selector, and menu
* '''Main chat window''' - Conversation view and message input

=== 3.2 Left Sidebar ===

==== Chat history list ====
Each row shows:
* The conversation title
* The model used for that conversation

To open a conversation, select it from the list.

==== Model selector ====
Choose which AI model to use for new conversations:
* '''GPT-4o''' - OpenAI's most famous model
* '''GPT-5.2 Pro''' - OpenAI's advanced reasoning model
* '''Claude Sonnet 4.5''' - Anthropic's general model
* '''Gemini-3 Flash''' - Google's fast model

'''Note''' - Models cannot be changed mid-conversation. Start a new chat to use a different model.

==== Menu items ====
* '''Account''' - View your profile and sign out
* '''Settings''' - Theme, colors, and custom instructions
* '''Insights''' - Editorial analytics dashboard
* '''Help''' - Link to documentation
* '''Sign Out''' - End your session

=== 3.3 Main Chat Window ===

==== Header ====
Shows the conversation title and current model badge.

==== Messages ====
* Your messages appear on the right
* Assistant messages appear on the left
* Hover over assistant messages to reveal the copy button

==== Message input ====
Type your message and press Enter or click Send.

== 4. Sending Messages ==

=== 4.1 Basic messaging ===
# Type your message in the input field
# Press '''Enter''' or click '''Send'''
# Wait for the assistant to respond

=== 4.2 Multi-line messages ===
Press '''Shift+Enter''' to create a new line without sending.

=== 4.3 Stop generation ===
While the assistant is responding, click '''Stop''' to halt generation early.

== 5. Options Menu ==

The '''Options''' button inside the message input area provides access to:
* File uploads
* Prompt templates
* Quick actions

=== 5.1 Opening Options ===
Click the '''Options''' button to reveal the dropdown menu.

== 6. File Uploads ==

=== 6.1 Upload a file ===
# Click '''Options'''
# Select '''Upload files'''
# Choose one or more files

=== 6.2 Supported file types ===
* '''Text:''' .txt, .md, .csv, .tsv, .json
* '''Documents:''' .pdf, .doc, .docx
* '''Presentations:''' .ppt, .pptx
* '''Spreadsheets:''' .xls, .xlsx
* '''Images:''' .png, .jpg, .gif, .webp, .bmp, .tiff

=== 6.3 File status ===
Uploaded files appear as chips above the input:
* '''Uploaded''' - File received
* '''Parsed''' - Text extracted and available to the model

=== 6.4 Remove a file ===
Click the '''×''' on the file chip to remove it from the conversation.

=== 6.5 File size limit ===
Maximum upload size is 25 MB per file.

== 7. Prompt Templates ==

Templates provide structured prompts for common content types.

=== 7.1 Using a template ===
# Click '''Options'''
# Select a template from the list
# The template badge appears above the input
# Type your specific content or context
# Send your message

=== 7.2 Available templates ===

==== Landing Pages ====
{| class="wikitable"
! Template !! Description
|-
| Locations || Global offices and delivery centers
|-
| Services || Service overview
|-
| Industries || Industry overview or specialization page
|-
| Leadership || Leadership team
|-
| Clients || Client portfolio
|}

==== Case Studies ====
{| class="wikitable"
! Template !! Description
|-
| Case Study (PPT) || PowerPoint, single-page case study
|-
| Case Study (Website) || SEO-optimized case study with KPIs
|}

=== 7.3 Template behavior ===
* Templates automatically use '''Google Gemini''' for optimal results
* The template badge shows which template is active
* Click '''×''' on the badge to clear the template

== 8. Quick Actions ==

Quick actions transform the previous AI response with one click.

=== 8.1 Available quick actions ===
{| class="wikitable"
! Action !! Effect
|-
| Make it shorter || Condense to ~50% of original length
|-
| Make it more formal || Increase professional tone
|-
| Simplify this || Make clearer and more accessible
|-
| Expand on this || Add detail and elaboration
|}

=== 8.2 Using quick actions ===
# You must write a prompt and receive a message before you can run a quick action
# Click '''Options'''
# Select a quick action
# The action executes using Gemini 3

== 9. Editorial Insights ==

The Insights dashboard shows your personal editorial analytics.

=== 9.1 Accessing Insights ===
# Open the sidebar
# Click '''Insights''' in the menu

=== 9.2 Metrics displayed ===
* '''Total Messages''' - Number of messages processed
* '''Passed''' - Messages without AI pattern violations
* '''Violations''' - Messages where patterns were detected and corrected
* '''Pass Rate''' - Percentage of clean messages

=== 9.3 Top Violations ===
Shows the most common AI-typical words detected in your conversations, such as:
* "utilize" (instead of "use")
* "landscape" (overused in AI writing)
* "delve" (AI favorite)

=== 9.4 Recent Corrections ===
Examples of recent messages where the editorial system improved the output.

== 10. Conversation Export ==

Export your conversations for documentation or backup.

=== 10.1 Export formats ===
* '''Markdown''' - Formatted text file
* '''JSON''' - Structured data

=== 10.2 How to export ===
# Open the conversation you want to export
# Click the '''Export''' button in the header
# Select '''Markdown''' or '''JSON'''
# The file downloads automatically

== 11. Settings ==

=== 11.1 Theme ===
* '''Light''' - Light background
* '''Dark''' - Dark background
* '''System''' - Match your operating system preference

=== 11.2 Primary color ===
Choose an accent color for buttons and highlights.

=== 11.3 Custom instructions ===
Provide information about your preferences that the assistant should remember.

=== 11.4 LLM instructions ===
Add rules for how the assistant should respond in all conversations.

== 12. The Two-Pass Editorial System ==

Righting Sentences uses a unique two-pass system to improve AI output.

=== 12.1 How it works ===
# '''Pass 1:''' The AI generates a natural response
# '''Detection:''' The system identifies AI-typical patterns:
#* Banned words (e.g., "utilize", "landscape", "delve")
#* Three-part lists (triads)
#* Rhetorical patterns (e.g., "It's not X, it's Y")
# '''Pass 2:''' The AI regenerates with stricter guidelines
# '''Post-processing:''' Any remaining issues are cleaned programmatically

=== 12.2 Why it matters ===
AI models tend to overuse certain words and patterns that make text sound artificial. The editorial system produces writing that sounds more natural and human-like.

=== 12.3 Banned words ===
The system currently flags: utilize, landscape, unlock, critical, guardrails, tracks, shape, shift, teams, delve, tapestry.

=== 12.4 Triad exceptions ===
Some three-part phrases are culturally significant and exempt from editing:
* "executive, legislative, and judicial"
* "life, liberty, and the pursuit of happiness"
* "red, white, and blue"

== 13. Troubleshooting ==

=== 13.1 I cannot sign in ===
* Confirm you are using a Google account
* Confirm your account has been invited
* Contact Saxton Publishing if the problem persists

=== 13.2 I cannot change the model ===
Models cannot be changed mid-conversation. Start a new chat to use a different model.

=== 13.3 Quick actions are not available ===
Quick actions require at least one assistant message in the conversation. Send a message first, then use quick actions.

=== 13.4 Template is not working ===
* Ensure the template badge is visible above the input
* Templates require you to provide context in your message
* If issues persist, clear the template and try again

=== 13.5 File upload fails ===
* Check that the file is under 25 MB
* Verify the file type is supported
* Contact the administrator if errors persist

== 14. Data and Privacy ==

=== 14.1 What is stored ===
* Conversations and messages
* Uploaded files
* Editorial logs (for system improvement)

=== 14.2 Where data is stored ===
* Google Cloud Firestore (conversations, metadata)
* Google Cloud Storage (uploaded files)

=== 14.3 Third-party providers ===
Messages are sent to the selected model provider (OpenAI, Anthropic, or Google) to generate responses.

----
''Righting Sentences is developed by Saxton Publishing.''

[[Category:Righting Sentences]]
[[Category:User Guide]]

Righting Sentences User Guide - 4.0

2026-02-07T00:05:12Z

Saxtonmd77: /* 8.2 Using quick actions */

'''Righting Sentences''' — User Guide (v4.0)

Last updated: February 2026

Production URL: https://righting-sentences-573737403792.us-east1.run.app/

__TOC__

== 1. Purpose and Scope ==
Righting Sentences is a web-based chat application that generates AI text that reads more like standard written English. This application is a data science project that includes a unique two-pass editorial system, the Morey Language Model which automatically detects and removes AI-typical language patterns. Usage improves the Morey Language Model, an editorial system that eventually will include a fine-tuned foundational LLM.

== 2. Access and Authentication ==

=== 2.1 Google account required ===
To use the application, you must sign in with a Google account.

=== 2.2 Invitation-only access ===
Access is provided by invitation. If you cannot sign in or do not see the application after signing in, contact the administrator at https://saxtonpublishing.com/contact/.

=== 2.3 Sign in ===
# Navigate to the production URL
# Select '''Sign in with Google'''
# Complete Google authentication
# After sign-in, you will see the main chat interface

== 3. User Interface ==

=== 3.1 Layout overview ===
The interface has two main areas:
* '''Left sidebar''' - Chat history, model selector, and menu
* '''Main chat window''' - Conversation view and message input

=== 3.2 Left Sidebar ===

==== Chat history list ====
Each row shows:
* The conversation title
* The model used for that conversation

To open a conversation, select it from the list.

==== Model selector ====
Choose which AI model to use for new conversations:
* '''GPT-4o''' - OpenAI's most famous model
* '''GPT-5.2 Pro''' - OpenAI's advanced reasoning model
* '''Claude Sonnet 4.5''' - Anthropic's general model
* '''Gemini-3 Flash''' - Google's fast model

'''Note''' - Models cannot be changed mid-conversation. Start a new chat to use a different model.

==== Menu items ====
* '''Account''' - View your profile and sign out
* '''Settings''' - Theme, colors, and custom instructions
* '''Insights''' - Editorial analytics dashboard
* '''Help''' - Link to documentation
* '''Sign Out''' - End your session

=== 3.3 Main Chat Window ===

==== Header ====
Shows the conversation title and current model badge.

==== Messages ====
* Your messages appear on the right
* Assistant messages appear on the left
* Hover over assistant messages to reveal the copy button

==== Message input ====
Type your message and press Enter or click Send.

== 4. Sending Messages ==

=== 4.1 Basic messaging ===
# Type your message in the input field
# Press '''Enter''' or click '''Send'''
# Wait for the assistant to respond

=== 4.2 Multi-line messages ===
Press '''Shift+Enter''' to create a new line without sending.

=== 4.3 Stop generation ===
While the assistant is responding, click '''Stop''' to halt generation early.

== 5. Options Menu ==

The '''Options''' button inside the message input area provides access to:
* File uploads
* Prompt templates
* Quick actions

=== 5.1 Opening Options ===
Click the '''Options''' button to reveal the dropdown menu.

== 6. File Uploads ==

=== 6.1 Upload a file ===
# Click '''Options'''
# Select '''Upload files'''
# Choose one or more files

=== 6.2 Supported file types ===
* '''Text:''' .txt, .md, .csv, .tsv, .json
* '''Documents:''' .pdf, .doc, .docx
* '''Presentations:''' .ppt, .pptx
* '''Spreadsheets:''' .xls, .xlsx
* '''Images:''' .png, .jpg, .gif, .webp, .bmp, .tiff

=== 6.3 File status ===
Uploaded files appear as chips above the input:
* '''Uploaded''' - File received
* '''Parsed''' - Text extracted and available to the model

=== 6.4 Remove a file ===
Click the '''×''' on the file chip to remove it from the conversation.

=== 6.5 File size limit ===
Maximum upload size is 25 MB per file.

== 7. Prompt Templates ==

Templates provide structured prompts for common content types.

=== 7.1 Using a template ===
# Click '''Options'''
# Select a template from the list
# The template badge appears above the input
# Type your specific content or context
# Send your message

=== 7.2 Available templates ===

==== Landing Pages ====
{| class="wikitable"
! Template !! Description
|-
| Locations || Global offices and delivery centers
|-
| Services || Service overview
|-
| Industries || Industry overview or specialization page
|-
| Leadership || Leadership team
|-
| Clients || Client portfolio
|}

==== Case Studies ====
{| class="wikitable"
! Template !! Description
|-
| Case Study (PPT) || PowerPoint, single-page case study
|-
| Case Study (Website) || SEO-optimized case study with KPIs
|}

=== 7.3 Template behavior ===
* Templates automatically use '''Google Gemini''' for optimal results
* The template badge shows which template is active
* Click '''×''' on the badge to clear the template

== 8. Quick Actions ==

Quick actions transform the previous AI response with one click.

=== 8.1 Available quick actions ===
{| class="wikitable"
! Action !! Effect
|-
| Make it shorter || Condense to ~50% of original length
|-
| Make it more formal || Increase professional tone
|-
| Simplify this || Make clearer and more accessible
|-
| Expand on this || Add detail and elaboration
|}

=== 8.2 Using quick actions ===
# You must write a prompt and receive a message before you can run a quick action
# Click '''Options'''
# Select a quick action
# The action executes using Gemini 3

=== 8.3 Quick action behavior ===
* Quick actions automatically reference the previous assistant response
* They use '''Google Gemini''' regardless of conversation model
* The transformed response appears as a new message

== 9. Editorial Insights ==

The Insights dashboard shows your personal editorial analytics.

=== 9.1 Accessing Insights ===
# Open the sidebar
# Click '''Insights''' in the menu

=== 9.2 Metrics displayed ===
* '''Total Messages''' - Number of messages processed
* '''Passed''' - Messages without AI pattern violations
* '''Violations''' - Messages where patterns were detected and corrected
* '''Pass Rate''' - Percentage of clean messages

=== 9.3 Top Violations ===
Shows the most common AI-typical words detected in your conversations, such as:
* "utilize" (instead of "use")
* "landscape" (overused in AI writing)
* "delve" (AI favorite)

=== 9.4 Recent Corrections ===
Examples of recent messages where the editorial system improved the output.

== 10. Conversation Export ==

Export your conversations for documentation or backup.

=== 10.1 Export formats ===
* '''Markdown''' - Formatted text file
* '''JSON''' - Structured data

=== 10.2 How to export ===
# Open the conversation you want to export
# Click the '''Export''' button in the header
# Select '''Markdown''' or '''JSON'''
# The file downloads automatically

== 11. Settings ==

=== 11.1 Theme ===
* '''Light''' - Light background
* '''Dark''' - Dark background
* '''System''' - Match your operating system preference

=== 11.2 Primary color ===
Choose an accent color for buttons and highlights.

=== 11.3 Custom instructions ===
Provide information about your preferences that the assistant should remember.

=== 11.4 LLM instructions ===
Add rules for how the assistant should respond in all conversations.

== 12. The Two-Pass Editorial System ==

Righting Sentences uses a unique two-pass system to improve AI output.

=== 12.1 How it works ===
# '''Pass 1:''' The AI generates a natural response
# '''Detection:''' The system identifies AI-typical patterns:
#* Banned words (e.g., "utilize", "landscape", "delve")
#* Three-part lists (triads)
#* Rhetorical patterns (e.g., "It's not X, it's Y")
# '''Pass 2:''' The AI regenerates with stricter guidelines
# '''Post-processing:''' Any remaining issues are cleaned programmatically

=== 12.2 Why it matters ===
AI models tend to overuse certain words and patterns that make text sound artificial. The editorial system produces writing that sounds more natural and human-like.

=== 12.3 Banned words ===
The system currently flags: utilize, landscape, unlock, critical, guardrails, tracks, shape, shift, teams, delve, tapestry.

=== 12.4 Triad exceptions ===
Some three-part phrases are culturally significant and exempt from editing:
* "executive, legislative, and judicial"
* "life, liberty, and the pursuit of happiness"
* "red, white, and blue"

== 13. Troubleshooting ==

=== 13.1 I cannot sign in ===
* Confirm you are using a Google account
* Confirm your account has been invited
* Contact Saxton Publishing if the problem persists

=== 13.2 I cannot change the model ===
Models cannot be changed mid-conversation. Start a new chat to use a different model.

=== 13.3 Quick actions are not available ===
Quick actions require at least one assistant message in the conversation. Send a message first, then use quick actions.

=== 13.4 Template is not working ===
* Ensure the template badge is visible above the input
* Templates require you to provide context in your message
* If issues persist, clear the template and try again

=== 13.5 File upload fails ===
* Check that the file is under 25 MB
* Verify the file type is supported
* Contact the administrator if errors persist

== 14. Data and Privacy ==

=== 14.1 What is stored ===
* Conversations and messages
* Uploaded files
* Editorial logs (for system improvement)

=== 14.2 Where data is stored ===
* Google Cloud Firestore (conversations, metadata)
* Google Cloud Storage (uploaded files)

=== 14.3 Third-party providers ===
Messages are sent to the selected model provider (OpenAI, Anthropic, or Google) to generate responses.

----
''Righting Sentences is developed by Saxton Publishing.''

[[Category:Righting Sentences]]
[[Category:User Guide]]

Righting Sentences User Guide - 4.0

2026-02-07T00:03:59Z

Saxtonmd77: /* Case Studies */

'''Righting Sentences''' — User Guide (v4.0)

Last updated: February 2026

Production URL: https://righting-sentences-573737403792.us-east1.run.app/

__TOC__

== 1. Purpose and Scope ==
Righting Sentences is a web-based chat application that generates AI text that reads more like standard written English. This application is a data science project that includes a unique two-pass editorial system, the Morey Language Model which automatically detects and removes AI-typical language patterns. Usage improves the Morey Language Model, an editorial system that eventually will include a fine-tuned foundational LLM.

== 2. Access and Authentication ==

=== 2.1 Google account required ===
To use the application, you must sign in with a Google account.

=== 2.2 Invitation-only access ===
Access is provided by invitation. If you cannot sign in or do not see the application after signing in, contact the administrator at https://saxtonpublishing.com/contact/.

=== 2.3 Sign in ===
# Navigate to the production URL
# Select '''Sign in with Google'''
# Complete Google authentication
# After sign-in, you will see the main chat interface

== 3. User Interface ==

=== 3.1 Layout overview ===
The interface has two main areas:
* '''Left sidebar''' - Chat history, model selector, and menu
* '''Main chat window''' - Conversation view and message input

=== 3.2 Left Sidebar ===

==== Chat history list ====
Each row shows:
* The conversation title
* The model used for that conversation

To open a conversation, select it from the list.

==== Model selector ====
Choose which AI model to use for new conversations:
* '''GPT-4o''' - OpenAI's most famous model
* '''GPT-5.2 Pro''' - OpenAI's advanced reasoning model
* '''Claude Sonnet 4.5''' - Anthropic's general model
* '''Gemini-3 Flash''' - Google's fast model

'''Note''' - Models cannot be changed mid-conversation. Start a new chat to use a different model.

==== Menu items ====
* '''Account''' - View your profile and sign out
* '''Settings''' - Theme, colors, and custom instructions
* '''Insights''' - Editorial analytics dashboard
* '''Help''' - Link to documentation
* '''Sign Out''' - End your session

=== 3.3 Main Chat Window ===

==== Header ====
Shows the conversation title and current model badge.

==== Messages ====
* Your messages appear on the right
* Assistant messages appear on the left
* Hover over assistant messages to reveal the copy button

==== Message input ====
Type your message and press Enter or click Send.

== 4. Sending Messages ==

=== 4.1 Basic messaging ===
# Type your message in the input field
# Press '''Enter''' or click '''Send'''
# Wait for the assistant to respond

=== 4.2 Multi-line messages ===
Press '''Shift+Enter''' to create a new line without sending.

=== 4.3 Stop generation ===
While the assistant is responding, click '''Stop''' to halt generation early.

== 5. Options Menu ==

The '''Options''' button inside the message input area provides access to:
* File uploads
* Prompt templates
* Quick actions

=== 5.1 Opening Options ===
Click the '''Options''' button to reveal the dropdown menu.

== 6. File Uploads ==

=== 6.1 Upload a file ===
# Click '''Options'''
# Select '''Upload files'''
# Choose one or more files

=== 6.2 Supported file types ===
* '''Text:''' .txt, .md, .csv, .tsv, .json
* '''Documents:''' .pdf, .doc, .docx
* '''Presentations:''' .ppt, .pptx
* '''Spreadsheets:''' .xls, .xlsx
* '''Images:''' .png, .jpg, .gif, .webp, .bmp, .tiff

=== 6.3 File status ===
Uploaded files appear as chips above the input:
* '''Uploaded''' - File received
* '''Parsed''' - Text extracted and available to the model

=== 6.4 Remove a file ===
Click the '''×''' on the file chip to remove it from the conversation.

=== 6.5 File size limit ===
Maximum upload size is 25 MB per file.

== 7. Prompt Templates ==

Templates provide structured prompts for common content types.

=== 7.1 Using a template ===
# Click '''Options'''
# Select a template from the list
# The template badge appears above the input
# Type your specific content or context
# Send your message

=== 7.2 Available templates ===

==== Landing Pages ====
{| class="wikitable"
! Template !! Description
|-
| Locations || Global offices and delivery centers
|-
| Services || Service overview
|-
| Industries || Industry overview or specialization page
|-
| Leadership || Leadership team
|-
| Clients || Client portfolio
|}

==== Case Studies ====
{| class="wikitable"
! Template !! Description
|-
| Case Study (PPT) || PowerPoint, single-page case study
|-
| Case Study (Website) || SEO-optimized case study with KPIs
|}

=== 7.3 Template behavior ===
* Templates automatically use '''Google Gemini''' for optimal results
* The template badge shows which template is active
* Click '''×''' on the badge to clear the template

== 8. Quick Actions ==

Quick actions transform the previous AI response with one click.

=== 8.1 Available quick actions ===
{| class="wikitable"
! Action !! Effect
|-
| Make it shorter || Condense to ~50% of original length
|-
| Make it more formal || Increase professional tone
|-
| Simplify this || Make clearer and more accessible
|-
| Expand on this || Add detail and elaboration
|}

=== 8.2 Using quick actions ===
# Ensure there is a previous assistant message in the conversation
# Click '''Options'''
# Select a quick action
# The action executes immediately (no additional prompt needed)

=== 8.3 Quick action behavior ===
* Quick actions automatically reference the previous assistant response
* They use '''Google Gemini''' regardless of conversation model
* The transformed response appears as a new message

== 9. Editorial Insights ==

The Insights dashboard shows your personal editorial analytics.

=== 9.1 Accessing Insights ===
# Open the sidebar
# Click '''Insights''' in the menu

=== 9.2 Metrics displayed ===
* '''Total Messages''' - Number of messages processed
* '''Passed''' - Messages without AI pattern violations
* '''Violations''' - Messages where patterns were detected and corrected
* '''Pass Rate''' - Percentage of clean messages

=== 9.3 Top Violations ===
Shows the most common AI-typical words detected in your conversations, such as:
* "utilize" (instead of "use")
* "landscape" (overused in AI writing)
* "delve" (AI favorite)

=== 9.4 Recent Corrections ===
Examples of recent messages where the editorial system improved the output.

== 10. Conversation Export ==

Export your conversations for documentation or backup.

=== 10.1 Export formats ===
* '''Markdown''' - Formatted text file
* '''JSON''' - Structured data

=== 10.2 How to export ===
# Open the conversation you want to export
# Click the '''Export''' button in the header
# Select '''Markdown''' or '''JSON'''
# The file downloads automatically

== 11. Settings ==

=== 11.1 Theme ===
* '''Light''' - Light background
* '''Dark''' - Dark background
* '''System''' - Match your operating system preference

=== 11.2 Primary color ===
Choose an accent color for buttons and highlights.

=== 11.3 Custom instructions ===
Provide information about your preferences that the assistant should remember.

=== 11.4 LLM instructions ===
Add rules for how the assistant should respond in all conversations.

== 12. The Two-Pass Editorial System ==

Righting Sentences uses a unique two-pass system to improve AI output.

=== 12.1 How it works ===
# '''Pass 1:''' The AI generates a natural response
# '''Detection:''' The system identifies AI-typical patterns:
#* Banned words (e.g., "utilize", "landscape", "delve")
#* Three-part lists (triads)
#* Rhetorical patterns (e.g., "It's not X, it's Y")
# '''Pass 2:''' The AI regenerates with stricter guidelines
# '''Post-processing:''' Any remaining issues are cleaned programmatically

=== 12.2 Why it matters ===
AI models tend to overuse certain words and patterns that make text sound artificial. The editorial system produces writing that sounds more natural and human-like.

=== 12.3 Banned words ===
The system currently flags: utilize, landscape, unlock, critical, guardrails, tracks, shape, shift, teams, delve, tapestry.

=== 12.4 Triad exceptions ===
Some three-part phrases are culturally significant and exempt from editing:
* "executive, legislative, and judicial"
* "life, liberty, and the pursuit of happiness"
* "red, white, and blue"

== 13. Troubleshooting ==

=== 13.1 I cannot sign in ===
* Confirm you are using a Google account
* Confirm your account has been invited
* Contact Saxton Publishing if the problem persists

=== 13.2 I cannot change the model ===
Models cannot be changed mid-conversation. Start a new chat to use a different model.

=== 13.3 Quick actions are not available ===
Quick actions require at least one assistant message in the conversation. Send a message first, then use quick actions.

=== 13.4 Template is not working ===
* Ensure the template badge is visible above the input
* Templates require you to provide context in your message
* If issues persist, clear the template and try again

=== 13.5 File upload fails ===
* Check that the file is under 25 MB
* Verify the file type is supported
* Contact the administrator if errors persist

== 14. Data and Privacy ==

=== 14.1 What is stored ===
* Conversations and messages
* Uploaded files
* Editorial logs (for system improvement)

=== 14.2 Where data is stored ===
* Google Cloud Firestore (conversations, metadata)
* Google Cloud Storage (uploaded files)

=== 14.3 Third-party providers ===
Messages are sent to the selected model provider (OpenAI, Anthropic, or Google) to generate responses.

----
''Righting Sentences is developed by Saxton Publishing.''

[[Category:Righting Sentences]]
[[Category:User Guide]]

Righting Sentences User Guide - 4.0

2026-02-07T00:03:23Z

Saxtonmd77: /* Landing Pages */

'''Righting Sentences''' — User Guide (v4.0)

Last updated: February 2026

Production URL: https://righting-sentences-573737403792.us-east1.run.app/

__TOC__

== 1. Purpose and Scope ==
Righting Sentences is a web-based chat application that generates AI text that reads more like standard written English. This application is a data science project that includes a unique two-pass editorial system, the Morey Language Model which automatically detects and removes AI-typical language patterns. Usage improves the Morey Language Model, an editorial system that eventually will include a fine-tuned foundational LLM.

== 2. Access and Authentication ==

=== 2.1 Google account required ===
To use the application, you must sign in with a Google account.

=== 2.2 Invitation-only access ===
Access is provided by invitation. If you cannot sign in or do not see the application after signing in, contact the administrator at https://saxtonpublishing.com/contact/.

=== 2.3 Sign in ===
# Navigate to the production URL
# Select '''Sign in with Google'''
# Complete Google authentication
# After sign-in, you will see the main chat interface

== 3. User Interface ==

=== 3.1 Layout overview ===
The interface has two main areas:
* '''Left sidebar''' - Chat history, model selector, and menu
* '''Main chat window''' - Conversation view and message input

=== 3.2 Left Sidebar ===

==== Chat history list ====
Each row shows:
* The conversation title
* The model used for that conversation

To open a conversation, select it from the list.

==== Model selector ====
Choose which AI model to use for new conversations:
* '''GPT-4o''' - OpenAI's most famous model
* '''GPT-5.2 Pro''' - OpenAI's advanced reasoning model
* '''Claude Sonnet 4.5''' - Anthropic's general model
* '''Gemini-3 Flash''' - Google's fast model

'''Note''' - Models cannot be changed mid-conversation. Start a new chat to use a different model.

==== Menu items ====
* '''Account''' - View your profile and sign out
* '''Settings''' - Theme, colors, and custom instructions
* '''Insights''' - Editorial analytics dashboard
* '''Help''' - Link to documentation
* '''Sign Out''' - End your session

=== 3.3 Main Chat Window ===

==== Header ====
Shows the conversation title and current model badge.

==== Messages ====
* Your messages appear on the right
* Assistant messages appear on the left
* Hover over assistant messages to reveal the copy button

==== Message input ====
Type your message and press Enter or click Send.

== 4. Sending Messages ==

=== 4.1 Basic messaging ===
# Type your message in the input field
# Press '''Enter''' or click '''Send'''
# Wait for the assistant to respond

=== 4.2 Multi-line messages ===
Press '''Shift+Enter''' to create a new line without sending.

=== 4.3 Stop generation ===
While the assistant is responding, click '''Stop''' to halt generation early.

== 5. Options Menu ==

The '''Options''' button inside the message input area provides access to:
* File uploads
* Prompt templates
* Quick actions

=== 5.1 Opening Options ===
Click the '''Options''' button to reveal the dropdown menu.

== 6. File Uploads ==

=== 6.1 Upload a file ===
# Click '''Options'''
# Select '''Upload files'''
# Choose one or more files

=== 6.2 Supported file types ===
* '''Text:''' .txt, .md, .csv, .tsv, .json
* '''Documents:''' .pdf, .doc, .docx
* '''Presentations:''' .ppt, .pptx
* '''Spreadsheets:''' .xls, .xlsx
* '''Images:''' .png, .jpg, .gif, .webp, .bmp, .tiff

=== 6.3 File status ===
Uploaded files appear as chips above the input:
* '''Uploaded''' - File received
* '''Parsed''' - Text extracted and available to the model

=== 6.4 Remove a file ===
Click the '''×''' on the file chip to remove it from the conversation.

=== 6.5 File size limit ===
Maximum upload size is 25 MB per file.

== 7. Prompt Templates ==

Templates provide structured prompts for common content types.

=== 7.1 Using a template ===
# Click '''Options'''
# Select a template from the list
# The template badge appears above the input
# Type your specific content or context
# Send your message

=== 7.2 Available templates ===

==== Landing Pages ====
{| class="wikitable"
! Template !! Description
|-
| Locations || Global offices and delivery centers
|-
| Services || Service overview
|-
| Industries || Industry overview or specialization page
|-
| Leadership || Leadership team
|-
| Clients || Client portfolio
|}

==== Case Studies ====
{| class="wikitable"
! Template !! Description
|-
| Case Study (PPT) || PowerPoint presentation structure (7 slides)
|-
| Case Study (Website) || Web-optimized case study with metrics
|}

=== 7.3 Template behavior ===
* Templates automatically use '''Google Gemini''' for optimal results
* The template badge shows which template is active
* Click '''×''' on the badge to clear the template

== 8. Quick Actions ==

Quick actions transform the previous AI response with one click.

=== 8.1 Available quick actions ===
{| class="wikitable"
! Action !! Effect
|-
| Make it shorter || Condense to ~50% of original length
|-
| Make it more formal || Increase professional tone
|-
| Simplify this || Make clearer and more accessible
|-
| Expand on this || Add detail and elaboration
|}

=== 8.2 Using quick actions ===
# Ensure there is a previous assistant message in the conversation
# Click '''Options'''
# Select a quick action
# The action executes immediately (no additional prompt needed)

=== 8.3 Quick action behavior ===
* Quick actions automatically reference the previous assistant response
* They use '''Google Gemini''' regardless of conversation model
* The transformed response appears as a new message

== 9. Editorial Insights ==

The Insights dashboard shows your personal editorial analytics.

=== 9.1 Accessing Insights ===
# Open the sidebar
# Click '''Insights''' in the menu

=== 9.2 Metrics displayed ===
* '''Total Messages''' - Number of messages processed
* '''Passed''' - Messages without AI pattern violations
* '''Violations''' - Messages where patterns were detected and corrected
* '''Pass Rate''' - Percentage of clean messages

=== 9.3 Top Violations ===
Shows the most common AI-typical words detected in your conversations, such as:
* "utilize" (instead of "use")
* "landscape" (overused in AI writing)
* "delve" (AI favorite)

=== 9.4 Recent Corrections ===
Examples of recent messages where the editorial system improved the output.

== 10. Conversation Export ==

Export your conversations for documentation or backup.

=== 10.1 Export formats ===
* '''Markdown''' - Formatted text file
* '''JSON''' - Structured data

=== 10.2 How to export ===
# Open the conversation you want to export
# Click the '''Export''' button in the header
# Select '''Markdown''' or '''JSON'''
# The file downloads automatically

== 11. Settings ==

=== 11.1 Theme ===
* '''Light''' - Light background
* '''Dark''' - Dark background
* '''System''' - Match your operating system preference

=== 11.2 Primary color ===
Choose an accent color for buttons and highlights.

=== 11.3 Custom instructions ===
Provide information about your preferences that the assistant should remember.

=== 11.4 LLM instructions ===
Add rules for how the assistant should respond in all conversations.

== 12. The Two-Pass Editorial System ==

Righting Sentences uses a unique two-pass system to improve AI output.

=== 12.1 How it works ===
# '''Pass 1:''' The AI generates a natural response
# '''Detection:''' The system identifies AI-typical patterns:
#* Banned words (e.g., "utilize", "landscape", "delve")
#* Three-part lists (triads)
#* Rhetorical patterns (e.g., "It's not X, it's Y")
# '''Pass 2:''' The AI regenerates with stricter guidelines
# '''Post-processing:''' Any remaining issues are cleaned programmatically

=== 12.2 Why it matters ===
AI models tend to overuse certain words and patterns that make text sound artificial. The editorial system produces writing that sounds more natural and human-like.

=== 12.3 Banned words ===
The system currently flags: utilize, landscape, unlock, critical, guardrails, tracks, shape, shift, teams, delve, tapestry.

=== 12.4 Triad exceptions ===
Some three-part phrases are culturally significant and exempt from editing:
* "executive, legislative, and judicial"
* "life, liberty, and the pursuit of happiness"
* "red, white, and blue"

== 13. Troubleshooting ==

=== 13.1 I cannot sign in ===
* Confirm you are using a Google account
* Confirm your account has been invited
* Contact Saxton Publishing if the problem persists

=== 13.2 I cannot change the model ===
Models cannot be changed mid-conversation. Start a new chat to use a different model.

=== 13.3 Quick actions are not available ===
Quick actions require at least one assistant message in the conversation. Send a message first, then use quick actions.

=== 13.4 Template is not working ===
* Ensure the template badge is visible above the input
* Templates require you to provide context in your message
* If issues persist, clear the template and try again

=== 13.5 File upload fails ===
* Check that the file is under 25 MB
* Verify the file type is supported
* Contact the administrator if errors persist

== 14. Data and Privacy ==

=== 14.1 What is stored ===
* Conversations and messages
* Uploaded files
* Editorial logs (for system improvement)

=== 14.2 Where data is stored ===
* Google Cloud Firestore (conversations, metadata)
* Google Cloud Storage (uploaded files)

=== 14.3 Third-party providers ===
Messages are sent to the selected model provider (OpenAI, Anthropic, or Google) to generate responses.

----
''Righting Sentences is developed by Saxton Publishing.''

[[Category:Righting Sentences]]
[[Category:User Guide]]

Righting Sentences User Guide - 4.0

2026-02-06T21:24:45Z

Saxtonmd77: /* 5. Options Menu */

'''Righting Sentences''' — User Guide (v4.0)

Last updated: February 2026

Production URL: https://righting-sentences-573737403792.us-east1.run.app/

__TOC__

== 1. Purpose and Scope ==
Righting Sentences is a web-based chat application that generates AI text that reads more like standard written English. This application is a data science project that includes a unique two-pass editorial system, the Morey Language Model which automatically detects and removes AI-typical language patterns. Usage improves the Morey Language Model, an editorial system that eventually will include a fine-tuned foundational LLM.

== 2. Access and Authentication ==

=== 2.1 Google account required ===
To use the application, you must sign in with a Google account.

=== 2.2 Invitation-only access ===
Access is provided by invitation. If you cannot sign in or do not see the application after signing in, contact the administrator at https://saxtonpublishing.com/contact/.

=== 2.3 Sign in ===
# Navigate to the production URL
# Select '''Sign in with Google'''
# Complete Google authentication
# After sign-in, you will see the main chat interface

== 3. User Interface ==

=== 3.1 Layout overview ===
The interface has two main areas:
* '''Left sidebar''' - Chat history, model selector, and menu
* '''Main chat window''' - Conversation view and message input

=== 3.2 Left Sidebar ===

==== Chat history list ====
Each row shows:
* The conversation title
* The model used for that conversation

To open a conversation, select it from the list.

==== Model selector ====
Choose which AI model to use for new conversations:
* '''GPT-4o''' - OpenAI's most famous model
* '''GPT-5.2 Pro''' - OpenAI's advanced reasoning model
* '''Claude Sonnet 4.5''' - Anthropic's general model
* '''Gemini-3 Flash''' - Google's fast model

'''Note''' - Models cannot be changed mid-conversation. Start a new chat to use a different model.

==== Menu items ====
* '''Account''' - View your profile and sign out
* '''Settings''' - Theme, colors, and custom instructions
* '''Insights''' - Editorial analytics dashboard
* '''Help''' - Link to documentation
* '''Sign Out''' - End your session

=== 3.3 Main Chat Window ===

==== Header ====
Shows the conversation title and current model badge.

==== Messages ====
* Your messages appear on the right
* Assistant messages appear on the left
* Hover over assistant messages to reveal the copy button

==== Message input ====
Type your message and press Enter or click Send.

== 4. Sending Messages ==

=== 4.1 Basic messaging ===
# Type your message in the input field
# Press '''Enter''' or click '''Send'''
# Wait for the assistant to respond

=== 4.2 Multi-line messages ===
Press '''Shift+Enter''' to create a new line without sending.

=== 4.3 Stop generation ===
While the assistant is responding, click '''Stop''' to halt generation early.

== 5. Options Menu ==

The '''Options''' button inside the message input area provides access to:
* File uploads
* Prompt templates
* Quick actions

=== 5.1 Opening Options ===
Click the '''Options''' button to reveal the dropdown menu.

== 6. File Uploads ==

=== 6.1 Upload a file ===
# Click '''Options'''
# Select '''Upload files'''
# Choose one or more files

=== 6.2 Supported file types ===
* '''Text:''' .txt, .md, .csv, .tsv, .json
* '''Documents:''' .pdf, .doc, .docx
* '''Presentations:''' .ppt, .pptx
* '''Spreadsheets:''' .xls, .xlsx
* '''Images:''' .png, .jpg, .gif, .webp, .bmp, .tiff

=== 6.3 File status ===
Uploaded files appear as chips above the input:
* '''Uploaded''' - File received
* '''Parsed''' - Text extracted and available to the model

=== 6.4 Remove a file ===
Click the '''×''' on the file chip to remove it from the conversation.

=== 6.5 File size limit ===
Maximum upload size is 25 MB per file.

== 7. Prompt Templates ==

Templates provide structured prompts for common content types.

=== 7.1 Using a template ===
# Click '''Options'''
# Select a template from the list
# The template badge appears above the input
# Type your specific content or context
# Send your message

=== 7.2 Available templates ===

==== Landing Pages ====
{| class="wikitable"
! Template !! Description
|-
| Locations || Global offices and delivery centers page
|-
| Services || Service overview with capabilities, proof, and outcomes
|-
| Industries || Industry overview or specialization page
|-
| Leadership || Leadership team introduction and credibility
|-
| Clients || Client portfolio and proof of impact
|}

==== Case Studies ====
{| class="wikitable"
! Template !! Description
|-
| Case Study (PPT) || PowerPoint presentation structure (7 slides)
|-
| Case Study (Website) || Web-optimized case study with metrics
|}

=== 7.3 Template behavior ===
* Templates automatically use '''Google Gemini''' for optimal results
* The template badge shows which template is active
* Click '''×''' on the badge to clear the template

== 8. Quick Actions ==

Quick actions transform the previous AI response with one click.

=== 8.1 Available quick actions ===
{| class="wikitable"
! Action !! Effect
|-
| Make it shorter || Condense to ~50% of original length
|-
| Make it more formal || Increase professional tone
|-
| Simplify this || Make clearer and more accessible
|-
| Expand on this || Add detail and elaboration
|}

=== 8.2 Using quick actions ===
# Ensure there is a previous assistant message in the conversation
# Click '''Options'''
# Select a quick action
# The action executes immediately (no additional prompt needed)

=== 8.3 Quick action behavior ===
* Quick actions automatically reference the previous assistant response
* They use '''Google Gemini''' regardless of conversation model
* The transformed response appears as a new message

== 9. Editorial Insights ==

The Insights dashboard shows your personal editorial analytics.

=== 9.1 Accessing Insights ===
# Open the sidebar
# Click '''Insights''' in the menu

=== 9.2 Metrics displayed ===
* '''Total Messages''' - Number of messages processed
* '''Passed''' - Messages without AI pattern violations
* '''Violations''' - Messages where patterns were detected and corrected
* '''Pass Rate''' - Percentage of clean messages

=== 9.3 Top Violations ===
Shows the most common AI-typical words detected in your conversations, such as:
* "utilize" (instead of "use")
* "landscape" (overused in AI writing)
* "delve" (AI favorite)

=== 9.4 Recent Corrections ===
Examples of recent messages where the editorial system improved the output.

== 10. Conversation Export ==

Export your conversations for documentation or backup.

=== 10.1 Export formats ===
* '''Markdown''' - Formatted text file
* '''JSON''' - Structured data

=== 10.2 How to export ===
# Open the conversation you want to export
# Click the '''Export''' button in the header
# Select '''Markdown''' or '''JSON'''
# The file downloads automatically

== 11. Settings ==

=== 11.1 Theme ===
* '''Light''' - Light background
* '''Dark''' - Dark background
* '''System''' - Match your operating system preference

=== 11.2 Primary color ===
Choose an accent color for buttons and highlights.

=== 11.3 Custom instructions ===
Provide information about your preferences that the assistant should remember.

=== 11.4 LLM instructions ===
Add rules for how the assistant should respond in all conversations.

== 12. The Two-Pass Editorial System ==

Righting Sentences uses a unique two-pass system to improve AI output.

=== 12.1 How it works ===
# '''Pass 1:''' The AI generates a natural response
# '''Detection:''' The system identifies AI-typical patterns:
#* Banned words (e.g., "utilize", "landscape", "delve")
#* Three-part lists (triads)
#* Rhetorical patterns (e.g., "It's not X, it's Y")
# '''Pass 2:''' The AI regenerates with stricter guidelines
# '''Post-processing:''' Any remaining issues are cleaned programmatically

=== 12.2 Why it matters ===
AI models tend to overuse certain words and patterns that make text sound artificial. The editorial system produces writing that sounds more natural and human-like.

=== 12.3 Banned words ===
The system currently flags: utilize, landscape, unlock, critical, guardrails, tracks, shape, shift, teams, delve, tapestry.

=== 12.4 Triad exceptions ===
Some three-part phrases are culturally significant and exempt from editing:
* "executive, legislative, and judicial"
* "life, liberty, and the pursuit of happiness"
* "red, white, and blue"

== 13. Troubleshooting ==

=== 13.1 I cannot sign in ===
* Confirm you are using a Google account
* Confirm your account has been invited
* Contact Saxton Publishing if the problem persists

=== 13.2 I cannot change the model ===
Models cannot be changed mid-conversation. Start a new chat to use a different model.

=== 13.3 Quick actions are not available ===
Quick actions require at least one assistant message in the conversation. Send a message first, then use quick actions.

=== 13.4 Template is not working ===
* Ensure the template badge is visible above the input
* Templates require you to provide context in your message
* If issues persist, clear the template and try again

=== 13.5 File upload fails ===
* Check that the file is under 25 MB
* Verify the file type is supported
* Contact the administrator if errors persist

== 14. Data and Privacy ==

=== 14.1 What is stored ===
* Conversations and messages
* Uploaded files
* Editorial logs (for system improvement)

=== 14.2 Where data is stored ===
* Google Cloud Firestore (conversations, metadata)
* Google Cloud Storage (uploaded files)

=== 14.3 Third-party providers ===
Messages are sent to the selected model provider (OpenAI, Anthropic, or Google) to generate responses.

----
''Righting Sentences is developed by Saxton Publishing.''

[[Category:Righting Sentences]]
[[Category:User Guide]]

Righting Sentences User Guide - 4.0

2026-02-06T21:22:04Z

Saxtonmd77: /* Model selector */

'''Righting Sentences''' — User Guide (v4.0)

Last updated: February 2026

Production URL: https://righting-sentences-573737403792.us-east1.run.app/

__TOC__

== 1. Purpose and Scope ==
Righting Sentences is a web-based chat application that generates AI text that reads more like standard written English. This application is a data science project that includes a unique two-pass editorial system, the Morey Language Model which automatically detects and removes AI-typical language patterns. Usage improves the Morey Language Model, an editorial system that eventually will include a fine-tuned foundational LLM.

== 2. Access and Authentication ==

=== 2.1 Google account required ===
To use the application, you must sign in with a Google account.

=== 2.2 Invitation-only access ===
Access is provided by invitation. If you cannot sign in or do not see the application after signing in, contact the administrator at https://saxtonpublishing.com/contact/.

=== 2.3 Sign in ===
# Navigate to the production URL
# Select '''Sign in with Google'''
# Complete Google authentication
# After sign-in, you will see the main chat interface

== 3. User Interface ==

=== 3.1 Layout overview ===
The interface has two main areas:
* '''Left sidebar''' - Chat history, model selector, and menu
* '''Main chat window''' - Conversation view and message input

=== 3.2 Left Sidebar ===

==== Chat history list ====
Each row shows:
* The conversation title
* The model used for that conversation

To open a conversation, select it from the list.

==== Model selector ====
Choose which AI model to use for new conversations:
* '''GPT-4o''' - OpenAI's most famous model
* '''GPT-5.2 Pro''' - OpenAI's advanced reasoning model
* '''Claude Sonnet 4.5''' - Anthropic's general model
* '''Gemini-3 Flash''' - Google's fast model

'''Note''' - Models cannot be changed mid-conversation. Start a new chat to use a different model.

==== Menu items ====
* '''Account''' - View your profile and sign out
* '''Settings''' - Theme, colors, and custom instructions
* '''Insights''' - Editorial analytics dashboard
* '''Help''' - Link to documentation
* '''Sign Out''' - End your session

=== 3.3 Main Chat Window ===

==== Header ====
Shows the conversation title and current model badge.

==== Messages ====
* Your messages appear on the right
* Assistant messages appear on the left
* Hover over assistant messages to reveal the copy button

==== Message input ====
Type your message and press Enter or click Send.

== 4. Sending Messages ==

=== 4.1 Basic messaging ===
# Type your message in the input field
# Press '''Enter''' or click '''Send'''
# Wait for the assistant to respond

=== 4.2 Multi-line messages ===
Press '''Shift+Enter''' to create a new line without sending.

=== 4.3 Stop generation ===
While the assistant is responding, click '''Stop''' to halt generation early.

== 5. Options Menu ==

The '''Options''' button inside the message input provides access to:
* File uploads
* Prompt templates
* Quick actions

=== 5.1 Opening Options ===
Click the '''Options''' button (three dots icon) to reveal the dropdown menu.

== 6. File Uploads ==

=== 6.1 Upload a file ===
# Click '''Options'''
# Select '''Upload files'''
# Choose one or more files

=== 6.2 Supported file types ===
* '''Text:''' .txt, .md, .csv, .tsv, .json
* '''Documents:''' .pdf, .doc, .docx
* '''Presentations:''' .ppt, .pptx
* '''Spreadsheets:''' .xls, .xlsx
* '''Images:''' .png, .jpg, .gif, .webp, .bmp, .tiff

=== 6.3 File status ===
Uploaded files appear as chips above the input:
* '''Uploaded''' - File received
* '''Parsed''' - Text extracted and available to the model

=== 6.4 Remove a file ===
Click the '''×''' on the file chip to remove it from the conversation.

=== 6.5 File size limit ===
Maximum upload size is 25 MB per file.

== 7. Prompt Templates ==

Templates provide structured prompts for common content types.

=== 7.1 Using a template ===
# Click '''Options'''
# Select a template from the list
# The template badge appears above the input
# Type your specific content or context
# Send your message

=== 7.2 Available templates ===

==== Landing Pages ====
{| class="wikitable"
! Template !! Description
|-
| Locations || Global offices and delivery centers page
|-
| Services || Service overview with capabilities, proof, and outcomes
|-
| Industries || Industry overview or specialization page
|-
| Leadership || Leadership team introduction and credibility
|-
| Clients || Client portfolio and proof of impact
|}

==== Case Studies ====
{| class="wikitable"
! Template !! Description
|-
| Case Study (PPT) || PowerPoint presentation structure (7 slides)
|-
| Case Study (Website) || Web-optimized case study with metrics
|}

=== 7.3 Template behavior ===
* Templates automatically use '''Google Gemini''' for optimal results
* The template badge shows which template is active
* Click '''×''' on the badge to clear the template

== 8. Quick Actions ==

Quick actions transform the previous AI response with one click.

=== 8.1 Available quick actions ===
{| class="wikitable"
! Action !! Effect
|-
| Make it shorter || Condense to ~50% of original length
|-
| Make it more formal || Increase professional tone
|-
| Simplify this || Make clearer and more accessible
|-
| Expand on this || Add detail and elaboration
|}

=== 8.2 Using quick actions ===
# Ensure there is a previous assistant message in the conversation
# Click '''Options'''
# Select a quick action
# The action executes immediately (no additional prompt needed)

=== 8.3 Quick action behavior ===
* Quick actions automatically reference the previous assistant response
* They use '''Google Gemini''' regardless of conversation model
* The transformed response appears as a new message

== 9. Editorial Insights ==

The Insights dashboard shows your personal editorial analytics.

=== 9.1 Accessing Insights ===
# Open the sidebar
# Click '''Insights''' in the menu

=== 9.2 Metrics displayed ===
* '''Total Messages''' - Number of messages processed
* '''Passed''' - Messages without AI pattern violations
* '''Violations''' - Messages where patterns were detected and corrected
* '''Pass Rate''' - Percentage of clean messages

=== 9.3 Top Violations ===
Shows the most common AI-typical words detected in your conversations, such as:
* "utilize" (instead of "use")
* "landscape" (overused in AI writing)
* "delve" (AI favorite)

=== 9.4 Recent Corrections ===
Examples of recent messages where the editorial system improved the output.

== 10. Conversation Export ==

Export your conversations for documentation or backup.

=== 10.1 Export formats ===
* '''Markdown''' - Formatted text file
* '''JSON''' - Structured data

=== 10.2 How to export ===
# Open the conversation you want to export
# Click the '''Export''' button in the header
# Select '''Markdown''' or '''JSON'''
# The file downloads automatically

== 11. Settings ==

=== 11.1 Theme ===
* '''Light''' - Light background
* '''Dark''' - Dark background
* '''System''' - Match your operating system preference

=== 11.2 Primary color ===
Choose an accent color for buttons and highlights.

=== 11.3 Custom instructions ===
Provide information about your preferences that the assistant should remember.

=== 11.4 LLM instructions ===
Add rules for how the assistant should respond in all conversations.

== 12. The Two-Pass Editorial System ==

Righting Sentences uses a unique two-pass system to improve AI output.

=== 12.1 How it works ===
# '''Pass 1:''' The AI generates a natural response
# '''Detection:''' The system identifies AI-typical patterns:
#* Banned words (e.g., "utilize", "landscape", "delve")
#* Three-part lists (triads)
#* Rhetorical patterns (e.g., "It's not X, it's Y")
# '''Pass 2:''' The AI regenerates with stricter guidelines
# '''Post-processing:''' Any remaining issues are cleaned programmatically

=== 12.2 Why it matters ===
AI models tend to overuse certain words and patterns that make text sound artificial. The editorial system produces writing that sounds more natural and human-like.

=== 12.3 Banned words ===
The system currently flags: utilize, landscape, unlock, critical, guardrails, tracks, shape, shift, teams, delve, tapestry.

=== 12.4 Triad exceptions ===
Some three-part phrases are culturally significant and exempt from editing:
* "executive, legislative, and judicial"
* "life, liberty, and the pursuit of happiness"
* "red, white, and blue"

== 13. Troubleshooting ==

=== 13.1 I cannot sign in ===
* Confirm you are using a Google account
* Confirm your account has been invited
* Contact Saxton Publishing if the problem persists

=== 13.2 I cannot change the model ===
Models cannot be changed mid-conversation. Start a new chat to use a different model.

=== 13.3 Quick actions are not available ===
Quick actions require at least one assistant message in the conversation. Send a message first, then use quick actions.

=== 13.4 Template is not working ===
* Ensure the template badge is visible above the input
* Templates require you to provide context in your message
* If issues persist, clear the template and try again

=== 13.5 File upload fails ===
* Check that the file is under 25 MB
* Verify the file type is supported
* Contact the administrator if errors persist

== 14. Data and Privacy ==

=== 14.1 What is stored ===
* Conversations and messages
* Uploaded files
* Editorial logs (for system improvement)

=== 14.2 Where data is stored ===
* Google Cloud Firestore (conversations, metadata)
* Google Cloud Storage (uploaded files)

=== 14.3 Third-party providers ===
Messages are sent to the selected model provider (OpenAI, Anthropic, or Google) to generate responses.

----
''Righting Sentences is developed by Saxton Publishing.''

[[Category:Righting Sentences]]
[[Category:User Guide]]

Righting Sentences User Guide - 4.0

2026-02-06T21:19:21Z

Saxtonmd77: /* 2.2 Invitation-only access */

'''Righting Sentences''' — User Guide (v4.0)

Last updated: February 2026

Production URL: https://righting-sentences-573737403792.us-east1.run.app/

__TOC__

== 1. Purpose and Scope ==
Righting Sentences is a web-based chat application that generates AI text that reads more like standard written English. This application is a data science project that includes a unique two-pass editorial system, the Morey Language Model which automatically detects and removes AI-typical language patterns. Usage improves the Morey Language Model, an editorial system that eventually will include a fine-tuned foundational LLM.

== 2. Access and Authentication ==

=== 2.1 Google account required ===
To use the application, you must sign in with a Google account.

=== 2.2 Invitation-only access ===
Access is provided by invitation. If you cannot sign in or do not see the application after signing in, contact the administrator at https://saxtonpublishing.com/contact/.

=== 2.3 Sign in ===
# Navigate to the production URL
# Select '''Sign in with Google'''
# Complete Google authentication
# After sign-in, you will see the main chat interface

== 3. User Interface ==

=== 3.1 Layout overview ===
The interface has two main areas:
* '''Left sidebar''' - Chat history, model selector, and menu
* '''Main chat window''' - Conversation view and message input

=== 3.2 Left Sidebar ===

==== Chat history list ====
Each row shows:
* The conversation title
* The model used for that conversation

To open a conversation, select it from the list.

==== Model selector ====
Choose which AI model to use for new conversations:
* '''GPT-4o''' - OpenAI's capable general-purpose model
* '''GPT-5.2 Pro''' - OpenAI's advanced reasoning model
* '''Claude Sonnet 4.5''' - Anthropic's balanced model
* '''Gemini-3 Flash''' - Google's fast, efficient model

'''Important:''' Models cannot be changed mid-conversation. Start a new chat to use a different model.

==== Menu items ====
* '''Account''' - View your profile and sign out
* '''Settings''' - Theme, colors, and custom instructions
* '''Insights''' - Editorial analytics dashboard
* '''Help''' - Link to documentation
* '''Sign Out''' - End your session

=== 3.3 Main Chat Window ===

==== Header ====
Shows the conversation title and current model badge.

==== Messages ====
* Your messages appear on the right
* Assistant messages appear on the left
* Hover over assistant messages to reveal the copy button

==== Message input ====
Type your message and press Enter or click Send.

== 4. Sending Messages ==

=== 4.1 Basic messaging ===
# Type your message in the input field
# Press '''Enter''' or click '''Send'''
# Wait for the assistant to respond

=== 4.2 Multi-line messages ===
Press '''Shift+Enter''' to create a new line without sending.

=== 4.3 Stop generation ===
While the assistant is responding, click '''Stop''' to halt generation early.

== 5. Options Menu ==

The '''Options''' button inside the message input provides access to:
* File uploads
* Prompt templates
* Quick actions

=== 5.1 Opening Options ===
Click the '''Options''' button (three dots icon) to reveal the dropdown menu.

== 6. File Uploads ==

=== 6.1 Upload a file ===
# Click '''Options'''
# Select '''Upload files'''
# Choose one or more files

=== 6.2 Supported file types ===
* '''Text:''' .txt, .md, .csv, .tsv, .json
* '''Documents:''' .pdf, .doc, .docx
* '''Presentations:''' .ppt, .pptx
* '''Spreadsheets:''' .xls, .xlsx
* '''Images:''' .png, .jpg, .gif, .webp, .bmp, .tiff

=== 6.3 File status ===
Uploaded files appear as chips above the input:
* '''Uploaded''' - File received
* '''Parsed''' - Text extracted and available to the model

=== 6.4 Remove a file ===
Click the '''×''' on the file chip to remove it from the conversation.

=== 6.5 File size limit ===
Maximum upload size is 25 MB per file.

== 7. Prompt Templates ==

Templates provide structured prompts for common content types.

=== 7.1 Using a template ===
# Click '''Options'''
# Select a template from the list
# The template badge appears above the input
# Type your specific content or context
# Send your message

=== 7.2 Available templates ===

==== Landing Pages ====
{| class="wikitable"
! Template !! Description
|-
| Locations || Global offices and delivery centers page
|-
| Services || Service overview with capabilities, proof, and outcomes
|-
| Industries || Industry overview or specialization page
|-
| Leadership || Leadership team introduction and credibility
|-
| Clients || Client portfolio and proof of impact
|}

==== Case Studies ====
{| class="wikitable"
! Template !! Description
|-
| Case Study (PPT) || PowerPoint presentation structure (7 slides)
|-
| Case Study (Website) || Web-optimized case study with metrics
|}

=== 7.3 Template behavior ===
* Templates automatically use '''Google Gemini''' for optimal results
* The template badge shows which template is active
* Click '''×''' on the badge to clear the template

== 8. Quick Actions ==

Quick actions transform the previous AI response with one click.

=== 8.1 Available quick actions ===
{| class="wikitable"
! Action !! Effect
|-
| Make it shorter || Condense to ~50% of original length
|-
| Make it more formal || Increase professional tone
|-
| Simplify this || Make clearer and more accessible
|-
| Expand on this || Add detail and elaboration
|}

=== 8.2 Using quick actions ===
# Ensure there is a previous assistant message in the conversation
# Click '''Options'''
# Select a quick action
# The action executes immediately (no additional prompt needed)

=== 8.3 Quick action behavior ===
* Quick actions automatically reference the previous assistant response
* They use '''Google Gemini''' regardless of conversation model
* The transformed response appears as a new message

== 9. Editorial Insights ==

The Insights dashboard shows your personal editorial analytics.

=== 9.1 Accessing Insights ===
# Open the sidebar
# Click '''Insights''' in the menu

=== 9.2 Metrics displayed ===
* '''Total Messages''' - Number of messages processed
* '''Passed''' - Messages without AI pattern violations
* '''Violations''' - Messages where patterns were detected and corrected
* '''Pass Rate''' - Percentage of clean messages

=== 9.3 Top Violations ===
Shows the most common AI-typical words detected in your conversations, such as:
* "utilize" (instead of "use")
* "landscape" (overused in AI writing)
* "delve" (AI favorite)

=== 9.4 Recent Corrections ===
Examples of recent messages where the editorial system improved the output.

== 10. Conversation Export ==

Export your conversations for documentation or backup.

=== 10.1 Export formats ===
* '''Markdown''' - Formatted text file
* '''JSON''' - Structured data

=== 10.2 How to export ===
# Open the conversation you want to export
# Click the '''Export''' button in the header
# Select '''Markdown''' or '''JSON'''
# The file downloads automatically

== 11. Settings ==

=== 11.1 Theme ===
* '''Light''' - Light background
* '''Dark''' - Dark background
* '''System''' - Match your operating system preference

=== 11.2 Primary color ===
Choose an accent color for buttons and highlights.

=== 11.3 Custom instructions ===
Provide information about your preferences that the assistant should remember.

=== 11.4 LLM instructions ===
Add rules for how the assistant should respond in all conversations.

== 12. The Two-Pass Editorial System ==

Righting Sentences uses a unique two-pass system to improve AI output.

=== 12.1 How it works ===
# '''Pass 1:''' The AI generates a natural response
# '''Detection:''' The system identifies AI-typical patterns:
#* Banned words (e.g., "utilize", "landscape", "delve")
#* Three-part lists (triads)
#* Rhetorical patterns (e.g., "It's not X, it's Y")
# '''Pass 2:''' The AI regenerates with stricter guidelines
# '''Post-processing:''' Any remaining issues are cleaned programmatically

=== 12.2 Why it matters ===
AI models tend to overuse certain words and patterns that make text sound artificial. The editorial system produces writing that sounds more natural and human-like.

=== 12.3 Banned words ===
The system currently flags: utilize, landscape, unlock, critical, guardrails, tracks, shape, shift, teams, delve, tapestry.

=== 12.4 Triad exceptions ===
Some three-part phrases are culturally significant and exempt from editing:
* "executive, legislative, and judicial"
* "life, liberty, and the pursuit of happiness"
* "red, white, and blue"

== 13. Troubleshooting ==

=== 13.1 I cannot sign in ===
* Confirm you are using a Google account
* Confirm your account has been invited
* Contact Saxton Publishing if the problem persists

=== 13.2 I cannot change the model ===
Models cannot be changed mid-conversation. Start a new chat to use a different model.

=== 13.3 Quick actions are not available ===
Quick actions require at least one assistant message in the conversation. Send a message first, then use quick actions.

=== 13.4 Template is not working ===
* Ensure the template badge is visible above the input
* Templates require you to provide context in your message
* If issues persist, clear the template and try again

=== 13.5 File upload fails ===
* Check that the file is under 25 MB
* Verify the file type is supported
* Contact the administrator if errors persist

== 14. Data and Privacy ==

=== 14.1 What is stored ===
* Conversations and messages
* Uploaded files
* Editorial logs (for system improvement)

=== 14.2 Where data is stored ===
* Google Cloud Firestore (conversations, metadata)
* Google Cloud Storage (uploaded files)

=== 14.3 Third-party providers ===
Messages are sent to the selected model provider (OpenAI, Anthropic, or Google) to generate responses.

----
''Righting Sentences is developed by Saxton Publishing.''

[[Category:Righting Sentences]]
[[Category:User Guide]]

Righting Sentences User Guide - 4.0

2026-02-06T21:17:42Z

Saxtonmd77: /* 1. Purpose and Scope */

'''Righting Sentences''' — User Guide (v4.0)

Last updated: February 2026

Production URL: https://righting-sentences-573737403792.us-east1.run.app/

__TOC__

== 1. Purpose and Scope ==
Righting Sentences is a web-based chat application that generates AI text that reads more like standard written English. This application is a data science project that includes a unique two-pass editorial system, the Morey Language Model which automatically detects and removes AI-typical language patterns. Usage improves the Morey Language Model, an editorial system that eventually will include a fine-tuned foundational LLM.

== 2. Access and Authentication ==

=== 2.1 Google account required ===
To use the application, you must sign in with a Google account.

=== 2.2 Invitation-only access ===
Access is provided by invitation. If you cannot sign in or do not see the application after signing in, contact the administrator (Saxton Publishing).

=== 2.3 Sign in ===
# Navigate to the production URL
# Select '''Sign in with Google'''
# Complete Google authentication
# After sign-in, you will see the main chat interface

== 3. User Interface ==

=== 3.1 Layout overview ===
The interface has two main areas:
* '''Left sidebar''' - Chat history, model selector, and menu
* '''Main chat window''' - Conversation view and message input

=== 3.2 Left Sidebar ===

==== Chat history list ====
Each row shows:
* The conversation title
* The model used for that conversation

To open a conversation, select it from the list.

==== Model selector ====
Choose which AI model to use for new conversations:
* '''GPT-4o''' - OpenAI's capable general-purpose model
* '''GPT-5.2 Pro''' - OpenAI's advanced reasoning model
* '''Claude Sonnet 4.5''' - Anthropic's balanced model
* '''Gemini-3 Flash''' - Google's fast, efficient model

'''Important:''' Models cannot be changed mid-conversation. Start a new chat to use a different model.

==== Menu items ====
* '''Account''' - View your profile and sign out
* '''Settings''' - Theme, colors, and custom instructions
* '''Insights''' - Editorial analytics dashboard
* '''Help''' - Link to documentation
* '''Sign Out''' - End your session

=== 3.3 Main Chat Window ===

==== Header ====
Shows the conversation title and current model badge.

==== Messages ====
* Your messages appear on the right
* Assistant messages appear on the left
* Hover over assistant messages to reveal the copy button

==== Message input ====
Type your message and press Enter or click Send.

== 4. Sending Messages ==

=== 4.1 Basic messaging ===
# Type your message in the input field
# Press '''Enter''' or click '''Send'''
# Wait for the assistant to respond

=== 4.2 Multi-line messages ===
Press '''Shift+Enter''' to create a new line without sending.

=== 4.3 Stop generation ===
While the assistant is responding, click '''Stop''' to halt generation early.

== 5. Options Menu ==

The '''Options''' button inside the message input provides access to:
* File uploads
* Prompt templates
* Quick actions

=== 5.1 Opening Options ===
Click the '''Options''' button (three dots icon) to reveal the dropdown menu.

== 6. File Uploads ==

=== 6.1 Upload a file ===
# Click '''Options'''
# Select '''Upload files'''
# Choose one or more files

=== 6.2 Supported file types ===
* '''Text:''' .txt, .md, .csv, .tsv, .json
* '''Documents:''' .pdf, .doc, .docx
* '''Presentations:''' .ppt, .pptx
* '''Spreadsheets:''' .xls, .xlsx
* '''Images:''' .png, .jpg, .gif, .webp, .bmp, .tiff

=== 6.3 File status ===
Uploaded files appear as chips above the input:
* '''Uploaded''' - File received
* '''Parsed''' - Text extracted and available to the model

=== 6.4 Remove a file ===
Click the '''×''' on the file chip to remove it from the conversation.

=== 6.5 File size limit ===
Maximum upload size is 25 MB per file.

== 7. Prompt Templates ==

Templates provide structured prompts for common content types.

=== 7.1 Using a template ===
# Click '''Options'''
# Select a template from the list
# The template badge appears above the input
# Type your specific content or context
# Send your message

=== 7.2 Available templates ===

==== Landing Pages ====
{| class="wikitable"
! Template !! Description
|-
| Locations || Global offices and delivery centers page
|-
| Services || Service overview with capabilities, proof, and outcomes
|-
| Industries || Industry overview or specialization page
|-
| Leadership || Leadership team introduction and credibility
|-
| Clients || Client portfolio and proof of impact
|}

==== Case Studies ====
{| class="wikitable"
! Template !! Description
|-
| Case Study (PPT) || PowerPoint presentation structure (7 slides)
|-
| Case Study (Website) || Web-optimized case study with metrics
|}

=== 7.3 Template behavior ===
* Templates automatically use '''Google Gemini''' for optimal results
* The template badge shows which template is active
* Click '''×''' on the badge to clear the template

== 8. Quick Actions ==

Quick actions transform the previous AI response with one click.

=== 8.1 Available quick actions ===
{| class="wikitable"
! Action !! Effect
|-
| Make it shorter || Condense to ~50% of original length
|-
| Make it more formal || Increase professional tone
|-
| Simplify this || Make clearer and more accessible
|-
| Expand on this || Add detail and elaboration
|}

=== 8.2 Using quick actions ===
# Ensure there is a previous assistant message in the conversation
# Click '''Options'''
# Select a quick action
# The action executes immediately (no additional prompt needed)

=== 8.3 Quick action behavior ===
* Quick actions automatically reference the previous assistant response
* They use '''Google Gemini''' regardless of conversation model
* The transformed response appears as a new message

== 9. Editorial Insights ==

The Insights dashboard shows your personal editorial analytics.

=== 9.1 Accessing Insights ===
# Open the sidebar
# Click '''Insights''' in the menu

=== 9.2 Metrics displayed ===
* '''Total Messages''' - Number of messages processed
* '''Passed''' - Messages without AI pattern violations
* '''Violations''' - Messages where patterns were detected and corrected
* '''Pass Rate''' - Percentage of clean messages

=== 9.3 Top Violations ===
Shows the most common AI-typical words detected in your conversations, such as:
* "utilize" (instead of "use")
* "landscape" (overused in AI writing)
* "delve" (AI favorite)

=== 9.4 Recent Corrections ===
Examples of recent messages where the editorial system improved the output.

== 10. Conversation Export ==

Export your conversations for documentation or backup.

=== 10.1 Export formats ===
* '''Markdown''' - Formatted text file
* '''JSON''' - Structured data

=== 10.2 How to export ===
# Open the conversation you want to export
# Click the '''Export''' button in the header
# Select '''Markdown''' or '''JSON'''
# The file downloads automatically

== 11. Settings ==

=== 11.1 Theme ===
* '''Light''' - Light background
* '''Dark''' - Dark background
* '''System''' - Match your operating system preference

=== 11.2 Primary color ===
Choose an accent color for buttons and highlights.

=== 11.3 Custom instructions ===
Provide information about your preferences that the assistant should remember.

=== 11.4 LLM instructions ===
Add rules for how the assistant should respond in all conversations.

== 12. The Two-Pass Editorial System ==

Righting Sentences uses a unique two-pass system to improve AI output.

=== 12.1 How it works ===
# '''Pass 1:''' The AI generates a natural response
# '''Detection:''' The system identifies AI-typical patterns:
#* Banned words (e.g., "utilize", "landscape", "delve")
#* Three-part lists (triads)
#* Rhetorical patterns (e.g., "It's not X, it's Y")
# '''Pass 2:''' The AI regenerates with stricter guidelines
# '''Post-processing:''' Any remaining issues are cleaned programmatically

=== 12.2 Why it matters ===
AI models tend to overuse certain words and patterns that make text sound artificial. The editorial system produces writing that sounds more natural and human-like.

=== 12.3 Banned words ===
The system currently flags: utilize, landscape, unlock, critical, guardrails, tracks, shape, shift, teams, delve, tapestry.

=== 12.4 Triad exceptions ===
Some three-part phrases are culturally significant and exempt from editing:
* "executive, legislative, and judicial"
* "life, liberty, and the pursuit of happiness"
* "red, white, and blue"

== 13. Troubleshooting ==

=== 13.1 I cannot sign in ===
* Confirm you are using a Google account
* Confirm your account has been invited
* Contact Saxton Publishing if the problem persists

=== 13.2 I cannot change the model ===
Models cannot be changed mid-conversation. Start a new chat to use a different model.

=== 13.3 Quick actions are not available ===
Quick actions require at least one assistant message in the conversation. Send a message first, then use quick actions.

=== 13.4 Template is not working ===
* Ensure the template badge is visible above the input
* Templates require you to provide context in your message
* If issues persist, clear the template and try again

=== 13.5 File upload fails ===
* Check that the file is under 25 MB
* Verify the file type is supported
* Contact the administrator if errors persist

== 14. Data and Privacy ==

=== 14.1 What is stored ===
* Conversations and messages
* Uploaded files
* Editorial logs (for system improvement)

=== 14.2 Where data is stored ===
* Google Cloud Firestore (conversations, metadata)
* Google Cloud Storage (uploaded files)

=== 14.3 Third-party providers ===
Messages are sent to the selected model provider (OpenAI, Anthropic, or Google) to generate responses.

----
''Righting Sentences is developed by Saxton Publishing.''

[[Category:Righting Sentences]]
[[Category:User Guide]]

Righting Sentences User Guide - 4.0

2026-02-06T21:09:06Z

Saxtonmd77: /* 1. Purpose and Scope */

'''Righting Sentences''' — User Guide (v4.0)

Last updated: February 2026

Production URL: https://righting-sentences-573737403792.us-east1.run.app/

__TOC__

== 1. Purpose and Scope ==
'''Righting Sentences''' is a web-based chat application that helps you write and revise text in standard written English using modern generative AI (GenAI) models.

The application features a unique '''two-pass editorial system''' that automatically detects and removes AI-typical language patterns, producing text that sounds more natural.

This service is a '''data science''' project. Your usage helps improve editorial rules and model behavior over time.

=== 1.1 Who this is for ===
* You want help drafting, revising, or polishing writing
* You want alternative phrasings, summaries, or structured outputs (lists, outlines, tables)
* You want to discuss a document you upload (text, office files, PDFs, images)
* You need to create professional content like landing pages or case studies

=== 1.2 What this is not ===
* It is not a source of guaranteed factual truth
* It is not a substitute for professional advice (legal, medical, financial)

== 2. Access and Authentication ==

=== 2.1 Google account required ===
To use the application, you must sign in with a Google account.

=== 2.2 Invitation-only access ===
Access is provided by invitation. If you cannot sign in or do not see the application after signing in, contact the administrator (Saxton Publishing).

=== 2.3 Sign in ===
# Navigate to the production URL
# Select '''Sign in with Google'''
# Complete Google authentication
# After sign-in, you will see the main chat interface

== 3. User Interface ==

=== 3.1 Layout overview ===
The interface has two main areas:
* '''Left sidebar''' - Chat history, model selector, and menu
* '''Main chat window''' - Conversation view and message input

=== 3.2 Left Sidebar ===

==== Chat history list ====
Each row shows:
* The conversation title
* The model used for that conversation

To open a conversation, select it from the list.

==== Model selector ====
Choose which AI model to use for new conversations:
* '''GPT-4o''' - OpenAI's capable general-purpose model
* '''GPT-5.2 Pro''' - OpenAI's advanced reasoning model
* '''Claude Sonnet 4.5''' - Anthropic's balanced model
* '''Gemini-3 Flash''' - Google's fast, efficient model

'''Important:''' Models cannot be changed mid-conversation. Start a new chat to use a different model.

==== Menu items ====
* '''Account''' - View your profile and sign out
* '''Settings''' - Theme, colors, and custom instructions
* '''Insights''' - Editorial analytics dashboard
* '''Help''' - Link to documentation
* '''Sign Out''' - End your session

=== 3.3 Main Chat Window ===

==== Header ====
Shows the conversation title and current model badge.

==== Messages ====
* Your messages appear on the right
* Assistant messages appear on the left
* Hover over assistant messages to reveal the copy button

==== Message input ====
Type your message and press Enter or click Send.

== 4. Sending Messages ==

=== 4.1 Basic messaging ===
# Type your message in the input field
# Press '''Enter''' or click '''Send'''
# Wait for the assistant to respond

=== 4.2 Multi-line messages ===
Press '''Shift+Enter''' to create a new line without sending.

=== 4.3 Stop generation ===
While the assistant is responding, click '''Stop''' to halt generation early.

== 5. Options Menu ==

The '''Options''' button inside the message input provides access to:
* File uploads
* Prompt templates
* Quick actions

=== 5.1 Opening Options ===
Click the '''Options''' button (three dots icon) to reveal the dropdown menu.

== 6. File Uploads ==

=== 6.1 Upload a file ===
# Click '''Options'''
# Select '''Upload files'''
# Choose one or more files

=== 6.2 Supported file types ===
* '''Text:''' .txt, .md, .csv, .tsv, .json
* '''Documents:''' .pdf, .doc, .docx
* '''Presentations:''' .ppt, .pptx
* '''Spreadsheets:''' .xls, .xlsx
* '''Images:''' .png, .jpg, .gif, .webp, .bmp, .tiff

=== 6.3 File status ===
Uploaded files appear as chips above the input:
* '''Uploaded''' - File received
* '''Parsed''' - Text extracted and available to the model

=== 6.4 Remove a file ===
Click the '''×''' on the file chip to remove it from the conversation.

=== 6.5 File size limit ===
Maximum upload size is 25 MB per file.

== 7. Prompt Templates ==

Templates provide structured prompts for common content types.

=== 7.1 Using a template ===
# Click '''Options'''
# Select a template from the list
# The template badge appears above the input
# Type your specific content or context
# Send your message

=== 7.2 Available templates ===

==== Landing Pages ====
{| class="wikitable"
! Template !! Description
|-
| Locations || Global offices and delivery centers page
|-
| Services || Service overview with capabilities, proof, and outcomes
|-
| Industries || Industry overview or specialization page
|-
| Leadership || Leadership team introduction and credibility
|-
| Clients || Client portfolio and proof of impact
|}

==== Case Studies ====
{| class="wikitable"
! Template !! Description
|-
| Case Study (PPT) || PowerPoint presentation structure (7 slides)
|-
| Case Study (Website) || Web-optimized case study with metrics
|}

=== 7.3 Template behavior ===
* Templates automatically use '''Google Gemini''' for optimal results
* The template badge shows which template is active
* Click '''×''' on the badge to clear the template

== 8. Quick Actions ==

Quick actions transform the previous AI response with one click.

=== 8.1 Available quick actions ===
{| class="wikitable"
! Action !! Effect
|-
| Make it shorter || Condense to ~50% of original length
|-
| Make it more formal || Increase professional tone
|-
| Simplify this || Make clearer and more accessible
|-
| Expand on this || Add detail and elaboration
|}

=== 8.2 Using quick actions ===
# Ensure there is a previous assistant message in the conversation
# Click '''Options'''
# Select a quick action
# The action executes immediately (no additional prompt needed)

=== 8.3 Quick action behavior ===
* Quick actions automatically reference the previous assistant response
* They use '''Google Gemini''' regardless of conversation model
* The transformed response appears as a new message

== 9. Editorial Insights ==

The Insights dashboard shows your personal editorial analytics.

=== 9.1 Accessing Insights ===
# Open the sidebar
# Click '''Insights''' in the menu

=== 9.2 Metrics displayed ===
* '''Total Messages''' - Number of messages processed
* '''Passed''' - Messages without AI pattern violations
* '''Violations''' - Messages where patterns were detected and corrected
* '''Pass Rate''' - Percentage of clean messages

=== 9.3 Top Violations ===
Shows the most common AI-typical words detected in your conversations, such as:
* "utilize" (instead of "use")
* "landscape" (overused in AI writing)
* "delve" (AI favorite)

=== 9.4 Recent Corrections ===
Examples of recent messages where the editorial system improved the output.

== 10. Conversation Export ==

Export your conversations for documentation or backup.

=== 10.1 Export formats ===
* '''Markdown''' - Formatted text file
* '''JSON''' - Structured data

=== 10.2 How to export ===
# Open the conversation you want to export
# Click the '''Export''' button in the header
# Select '''Markdown''' or '''JSON'''
# The file downloads automatically

== 11. Settings ==

=== 11.1 Theme ===
* '''Light''' - Light background
* '''Dark''' - Dark background
* '''System''' - Match your operating system preference

=== 11.2 Primary color ===
Choose an accent color for buttons and highlights.

=== 11.3 Custom instructions ===
Provide information about your preferences that the assistant should remember.

=== 11.4 LLM instructions ===
Add rules for how the assistant should respond in all conversations.

== 12. The Two-Pass Editorial System ==

Righting Sentences uses a unique two-pass system to improve AI output.

=== 12.1 How it works ===
# '''Pass 1:''' The AI generates a natural response
# '''Detection:''' The system identifies AI-typical patterns:
#* Banned words (e.g., "utilize", "landscape", "delve")
#* Three-part lists (triads)
#* Rhetorical patterns (e.g., "It's not X, it's Y")
# '''Pass 2:''' The AI regenerates with stricter guidelines
# '''Post-processing:''' Any remaining issues are cleaned programmatically

=== 12.2 Why it matters ===
AI models tend to overuse certain words and patterns that make text sound artificial. The editorial system produces writing that sounds more natural and human-like.

=== 12.3 Banned words ===
The system currently flags: utilize, landscape, unlock, critical, guardrails, tracks, shape, shift, teams, delve, tapestry.

=== 12.4 Triad exceptions ===
Some three-part phrases are culturally significant and exempt from editing:
* "executive, legislative, and judicial"
* "life, liberty, and the pursuit of happiness"
* "red, white, and blue"

== 13. Troubleshooting ==

=== 13.1 I cannot sign in ===
* Confirm you are using a Google account
* Confirm your account has been invited
* Contact Saxton Publishing if the problem persists

=== 13.2 I cannot change the model ===
Models cannot be changed mid-conversation. Start a new chat to use a different model.

=== 13.3 Quick actions are not available ===
Quick actions require at least one assistant message in the conversation. Send a message first, then use quick actions.

=== 13.4 Template is not working ===
* Ensure the template badge is visible above the input
* Templates require you to provide context in your message
* If issues persist, clear the template and try again

=== 13.5 File upload fails ===
* Check that the file is under 25 MB
* Verify the file type is supported
* Contact the administrator if errors persist

== 14. Data and Privacy ==

=== 14.1 What is stored ===
* Conversations and messages
* Uploaded files
* Editorial logs (for system improvement)

=== 14.2 Where data is stored ===
* Google Cloud Firestore (conversations, metadata)
* Google Cloud Storage (uploaded files)

=== 14.3 Third-party providers ===
Messages are sent to the selected model provider (OpenAI, Anthropic, or Google) to generate responses.

----
''Righting Sentences is developed by Saxton Publishing.''

[[Category:Righting Sentences]]
[[Category:User Guide]]

Main Page

2026-02-06T19:40:36Z

Saxtonmd77: /* Categories on this Site */

= Matt Saxton’s Research & Notes =

Part of Saxton Publishing
https://www.saxtonpublishing.com

Created Dec. 14, 2025. Updates will appear here.

This site will be a collection of how-to articles, notes, reviews, data sheets, formulas, computer code, user guides, generative AI prompts, GenAI applications, lists of software repositories, and other technical documentation. But for now, it's just getting started. Users will find incomplete pages, pages that have not yet been created, and other possible bugs as the site is developed.

== Pages on this Site ==

* [[How to Create This Website]]
* [[Generative AI prompts]]
* [[GPT-5.2 Model Known Issues]]
* [[Matt’s Cars Data Project – Project Plan]]
* [[Righting Sentences AI - Release Notes-2.1]]
* [[Righting Sentences AI - Future Development Plans]]
* [[AI Chatbot Development]]
* [[Righting Sentences - React Frontend Migration]]
* [[Righting Sentences - Release Notes - 2.5]]
* [[Righting Sentences - User Guide]]
* [[Righting Sentences Changelog - 3.2-4.0]]
* [[Righting Sentences User Guide - 4.0]]
* [[Righting Sentences Release Notes - 4.0]]

== Depricated ==

These pages have been abandoned or replaced due to scope changes and substantial updates.

* [[GPT Humanizer Project]]

== Categories on this Site ==

[[Category:Righting Sentences]]
[[Category:Release Notes]]
[[Category:How-To Articles]]
[[Category:Projects]]

Main Page

2026-02-06T19:36:51Z

Saxtonmd77: /* Categories on this Site */

Main Page

2026-02-06T19:36:09Z

Saxtonmd77: /* Depricated */

Main Page

2026-02-06T19:35:59Z

Saxtonmd77: /* Categories on this Site */

Main Page

2026-02-06T19:35:27Z

Saxtonmd77: /* Categories on this Site */

= Matt Saxton’s Research & Notes =

Part of Saxton Publishing
https://www.saxtonpublishing.com

Created Dec. 14, 2025. Updates will appear here.

This site will be a collection of how-to articles, notes, reviews, data sheets, formulas, computer code, user guides, generative AI prompts, GenAI applications, lists of software repositories, and other technical documentation. But for now, it's just getting started. Users will find incomplete pages, pages that have not yet been created, and other possible bugs as the site is developed.

== Pages on this Site ==

* [[How to Create This Website]]
* [[Generative AI prompts]]
* [[GPT-5.2 Model Known Issues]]
* [[Matt’s Cars Data Project – Project Plan]]
* [[Righting Sentences AI - Release Notes-2.1]]
* [[Righting Sentences AI - Future Development Plans]]
* [[AI Chatbot Development]]
* [[Righting Sentences - React Frontend Migration]]
* [[Righting Sentences - Release Notes - 2.5]]
* [[Righting Sentences - User Guide]]
* [[Righting Sentences Changelog - 3.2-4.0]]
* [[Righting Sentences User Guide - 4.0]]
* [[Righting Sentences Release Notes - 4.0]]

== Categories on this Site ==

[[Category:Righting Sentences]]
[[Category:Release Notes]]

== Depricated ==

These pages have been abandoned or replaced due to scope changes and substantial updates.

* [[GPT Humanizer Project]]

Main Page

2026-02-06T19:34:59Z

Saxtonmd77: /* Pages on this Site */

= Matt Saxton’s Research & Notes =

Part of Saxton Publishing
https://www.saxtonpublishing.com

Created Dec. 14, 2025. Updates will appear here.

This site will be a collection of how-to articles, notes, reviews, data sheets, formulas, computer code, user guides, generative AI prompts, GenAI applications, lists of software repositories, and other technical documentation. But for now, it's just getting started. Users will find incomplete pages, pages that have not yet been created, and other possible bugs as the site is developed.

== Pages on this Site ==

* [[How to Create This Website]]
* [[Generative AI prompts]]
* [[GPT-5.2 Model Known Issues]]
* [[Matt’s Cars Data Project – Project Plan]]
* [[Righting Sentences AI - Release Notes-2.1]]
* [[Righting Sentences AI - Future Development Plans]]
* [[AI Chatbot Development]]
* [[Righting Sentences - React Frontend Migration]]
* [[Righting Sentences - Release Notes - 2.5]]
* [[Righting Sentences - User Guide]]
* [[Righting Sentences Changelog - 3.2-4.0]]
* [[Righting Sentences User Guide - 4.0]]
* [[Righting Sentences Release Notes - 4.0]]

== Categories on this Site ==

== Depricated ==

These pages have been abandoned or replaced due to scope changes and substantial updates.

* [[GPT Humanizer Project]]

Righting Sentences Release Notes - 4.0

2026-02-06T19:34:08Z

Saxtonmd77: /* Coming Soon */

= Righting Sentences v4.0 Release Notes =

'''Release Date:''' 6 February 2026

'''Production URL:''' https://righting-sentences-573737403792.us-east1.run.app/

== Overview ==

Righting Sentences v4.0 includes content creation tools with Prompt Templates and Quick Actions, along with an Editorial Insights dashboard that shows how the two-pass editorial system improves writing. This release also adds the ability to export conversations in some file formats.

== Highlights ==

=== Prompt Templates ===
Pre-built templates for professional content creation, optimized for B2B marketing use cases.

'''Landing Page Templates:'''
* '''Locations''' - Creates pages for global offices and delivery centers
* '''Services''' - Builds pages for the overview of services
* '''Industries''' - Generates pages for industries or specializations
* '''Leadership''' - Drafts pages for leadership team members
* '''Clients''' - Creates a client portfolio

'''Case Study Templates:'''
* '''Case Study (PPT)''' - Single-page PPT
* '''Case Study (Website)''' - SEO-optimized web case study with KPIs

All templates use Google Gemini.

=== Quick Actions ===
Edit the previous response in one click:

* '''Make it shorter''' - Condenses content to approximately 50% of the original length
* '''Make it more formal''' - Increases professional tone
* '''Simplify this''' - Clarifie content
* '''Expand on this''' - Adds

Quick actions do not require additional prompts.

=== Editorial Insights ===
A new dashboard showing the user's editorial analytics:

* '''Total Messages''' - Number of messages processed through the editorial system
* '''Pass Rate''' - Percentage of AI responses that passed without violations
* '''Top Violations''' - Most common AI patterns detected in conversations
* '''Recent Corrections''' - Examples of recent system corrections

This feature helps users understand how the two-pass system works and which AI patterns are most commonly corrected from their prompts. However, the insights are not necessarily indicative of how the system is functioning as a whole.

=== Conversation Export ===
Export conversations for documentation or backup:

* '''Markdown format''' - For documentation
* '''JSON format''' - Structured data

== Technical Improvements ==

=== New Components ===
* <code>template_registry.py</code> - Template loading and resolution
* <code>editorial_insights.py</code> - Statistics computation
* <code>rate_limiter.py</code> - Request rate limiting
* <code>logging_config.py</code> - Structured logging configuration
* <code>InsightsPage.jsx</code> - Editorial analyitcs UI component

=== Architecture ===
* Templates are defined in <code>templates.md</code>
* Template prompts are injected into both passes of the editorial system
* Quick actions make fast corrections to the previous response
* Analytics are computed based on the user's data from Firestore <code>editorial_logs</code>

=== Testing Infrastructure ===
* pytest configuration for backend tests
* Vitest setup for frontend component testing
* Development dependencies are separated into <code>requirements-dev.txt</code>

== Known Limitations ==

* Editorial insights are limited to the most recent 100 messages per user
* The system will periodically drop a word in the response, requiring closer editing

----
''Righting Sentences is developed by Saxton Publishing.''

[[Category:Righting Sentences]]
[[Category:Release Notes]]

Righting Sentences Release Notes - 4.0

2026-02-06T19:33:45Z

Saxtonmd77: /* Known Limitations */

= Righting Sentences v4.0 Release Notes =

'''Release Date:''' 6 February 2026

'''Production URL:''' https://righting-sentences-573737403792.us-east1.run.app/

== Overview ==

Righting Sentences v4.0 includes content creation tools with Prompt Templates and Quick Actions, along with an Editorial Insights dashboard that shows how the two-pass editorial system improves writing. This release also adds the ability to export conversations in some file formats.

== Highlights ==

=== Prompt Templates ===
Pre-built templates for professional content creation, optimized for B2B marketing use cases.

'''Landing Page Templates:'''
* '''Locations''' - Creates pages for global offices and delivery centers
* '''Services''' - Builds pages for the overview of services
* '''Industries''' - Generates pages for industries or specializations
* '''Leadership''' - Drafts pages for leadership team members
* '''Clients''' - Creates a client portfolio

'''Case Study Templates:'''
* '''Case Study (PPT)''' - Single-page PPT
* '''Case Study (Website)''' - SEO-optimized web case study with KPIs

All templates use Google Gemini.

=== Quick Actions ===
Edit the previous response in one click:

* '''Make it shorter''' - Condenses content to approximately 50% of the original length
* '''Make it more formal''' - Increases professional tone
* '''Simplify this''' - Clarifie content
* '''Expand on this''' - Adds

Quick actions do not require additional prompts.

=== Editorial Insights ===
A new dashboard showing the user's editorial analytics:

* '''Total Messages''' - Number of messages processed through the editorial system
* '''Pass Rate''' - Percentage of AI responses that passed without violations
* '''Top Violations''' - Most common AI patterns detected in conversations
* '''Recent Corrections''' - Examples of recent system corrections

This feature helps users understand how the two-pass system works and which AI patterns are most commonly corrected from their prompts. However, the insights are not necessarily indicative of how the system is functioning as a whole.

=== Conversation Export ===
Export conversations for documentation or backup:

* '''Markdown format''' - For documentation
* '''JSON format''' - Structured data

== Technical Improvements ==

=== New Components ===
* <code>template_registry.py</code> - Template loading and resolution
* <code>editorial_insights.py</code> - Statistics computation
* <code>rate_limiter.py</code> - Request rate limiting
* <code>logging_config.py</code> - Structured logging configuration
* <code>InsightsPage.jsx</code> - Editorial analyitcs UI component

=== Architecture ===
* Templates are defined in <code>templates.md</code>
* Template prompts are injected into both passes of the editorial system
* Quick actions make fast corrections to the previous response
* Analytics are computed based on the user's data from Firestore <code>editorial_logs</code>

=== Testing Infrastructure ===
* pytest configuration for backend tests
* Vitest setup for frontend component testing
* Development dependencies are separated into <code>requirements-dev.txt</code>

== Known Limitations ==

* Editorial insights are limited to the most recent 100 messages per user
* The system will periodically drop a word in the response, requiring closer editing

== Coming Soon ==

* Custom user templates
* BigQuery integration for aggregated editorial analytics
* A/B testing framework for prompt variants

----
''Righting Sentences is developed by Saxton Publishing.''

[[Category:Righting Sentences]]
[[Category:Release Notes]]

Righting Sentences Release Notes - 4.0

2026-02-06T19:32:11Z

Saxtonmd77: /* Upgrade Notes */

= Righting Sentences v4.0 Release Notes =

'''Release Date:''' 6 February 2026

'''Production URL:''' https://righting-sentences-573737403792.us-east1.run.app/

== Overview ==

Righting Sentences v4.0 includes content creation tools with Prompt Templates and Quick Actions, along with an Editorial Insights dashboard that shows how the two-pass editorial system improves writing. This release also adds the ability to export conversations in some file formats.

== Highlights ==

=== Prompt Templates ===
Pre-built templates for professional content creation, optimized for B2B marketing use cases.

'''Landing Page Templates:'''
* '''Locations''' - Creates pages for global offices and delivery centers
* '''Services''' - Builds pages for the overview of services
* '''Industries''' - Generates pages for industries or specializations
* '''Leadership''' - Drafts pages for leadership team members
* '''Clients''' - Creates a client portfolio

'''Case Study Templates:'''
* '''Case Study (PPT)''' - Single-page PPT
* '''Case Study (Website)''' - SEO-optimized web case study with KPIs

All templates use Google Gemini.

=== Quick Actions ===
Edit the previous response in one click:

* '''Make it shorter''' - Condenses content to approximately 50% of the original length
* '''Make it more formal''' - Increases professional tone
* '''Simplify this''' - Clarifie content
* '''Expand on this''' - Adds

Quick actions do not require additional prompts.

=== Editorial Insights ===
A new dashboard showing the user's editorial analytics:

* '''Total Messages''' - Number of messages processed through the editorial system
* '''Pass Rate''' - Percentage of AI responses that passed without violations
* '''Top Violations''' - Most common AI patterns detected in conversations
* '''Recent Corrections''' - Examples of recent system corrections

This feature helps users understand how the two-pass system works and which AI patterns are most commonly corrected from their prompts. However, the insights are not necessarily indicative of how the system is functioning as a whole.

=== Conversation Export ===
Export conversations for documentation or backup:

* '''Markdown format''' - For documentation
* '''JSON format''' - Structured data

== Technical Improvements ==

=== New Components ===
* <code>template_registry.py</code> - Template loading and resolution
* <code>editorial_insights.py</code> - Statistics computation
* <code>rate_limiter.py</code> - Request rate limiting
* <code>logging_config.py</code> - Structured logging configuration
* <code>InsightsPage.jsx</code> - Editorial analyitcs UI component

=== Architecture ===
* Templates are defined in <code>templates.md</code>
* Template prompts are injected into both passes of the editorial system
* Quick actions make fast corrections to the previous response
* Analytics are computed based on the user's data from Firestore <code>editorial_logs</code>

=== Testing Infrastructure ===
* pytest configuration for backend tests
* Vitest setup for frontend component testing
* Development dependencies are separated into <code>requirements-dev.txt</code>

== Known Limitations ==

* Templates are currently read-only (no custom template creation yet)
* Quick actions require at least one previous assistant message in the conversation
* Editorial insights are limited to the most recent 100 messages per user

== Coming Soon ==

* Custom user templates
* BigQuery integration for aggregated editorial analytics
* A/B testing framework for prompt variants

----
''Righting Sentences is developed by Saxton Publishing.''

[[Category:Righting Sentences]]
[[Category:Release Notes]]

Righting Sentences Release Notes - 4.0

2026-02-06T19:31:49Z

Saxtonmd77: /* Technical Improvements */

= Righting Sentences v4.0 Release Notes =

'''Release Date:''' 6 February 2026

'''Production URL:''' https://righting-sentences-573737403792.us-east1.run.app/

== Overview ==

Righting Sentences v4.0 includes content creation tools with Prompt Templates and Quick Actions, along with an Editorial Insights dashboard that shows how the two-pass editorial system improves writing. This release also adds the ability to export conversations in some file formats.

== Highlights ==

=== Prompt Templates ===
Pre-built templates for professional content creation, optimized for B2B marketing use cases.

'''Landing Page Templates:'''
* '''Locations''' - Creates pages for global offices and delivery centers
* '''Services''' - Builds pages for the overview of services
* '''Industries''' - Generates pages for industries or specializations
* '''Leadership''' - Drafts pages for leadership team members
* '''Clients''' - Creates a client portfolio

'''Case Study Templates:'''
* '''Case Study (PPT)''' - Single-page PPT
* '''Case Study (Website)''' - SEO-optimized web case study with KPIs

All templates use Google Gemini.

=== Quick Actions ===
Edit the previous response in one click:

* '''Make it shorter''' - Condenses content to approximately 50% of the original length
* '''Make it more formal''' - Increases professional tone
* '''Simplify this''' - Clarifie content
* '''Expand on this''' - Adds

Quick actions do not require additional prompts.

=== Editorial Insights ===
A new dashboard showing the user's editorial analytics:

* '''Total Messages''' - Number of messages processed through the editorial system
* '''Pass Rate''' - Percentage of AI responses that passed without violations
* '''Top Violations''' - Most common AI patterns detected in conversations
* '''Recent Corrections''' - Examples of recent system corrections

This feature helps users understand how the two-pass system works and which AI patterns are most commonly corrected from their prompts. However, the insights are not necessarily indicative of how the system is functioning as a whole.

=== Conversation Export ===
Export conversations for documentation or backup:

* '''Markdown format''' - For documentation
* '''JSON format''' - Structured data

== Technical Improvements ==

=== New Components ===
* <code>template_registry.py</code> - Template loading and resolution
* <code>editorial_insights.py</code> - Statistics computation
* <code>rate_limiter.py</code> - Request rate limiting
* <code>logging_config.py</code> - Structured logging configuration
* <code>InsightsPage.jsx</code> - Editorial analyitcs UI component

=== Architecture ===
* Templates are defined in <code>templates.md</code>
* Template prompts are injected into both passes of the editorial system
* Quick actions make fast corrections to the previous response
* Analytics are computed based on the user's data from Firestore <code>editorial_logs</code>

=== Testing Infrastructure ===
* pytest configuration for backend tests
* Vitest setup for frontend component testing
* Development dependencies are separated into <code>requirements-dev.txt</code>

== Upgrade Notes ==

=== For Users ===
No action required. New features are available immediately after deployment.

=== For Administrators ===
* The <code>/templates</code> endpoint is now available for template listing
* The <code>/insights</code> endpoint returns per-user editorial statistics
* Template-based requests automatically use Gemini regardless of selected model

== Known Limitations ==

* Templates are currently read-only (no custom template creation yet)
* Quick actions require at least one previous assistant message in the conversation
* Editorial insights are limited to the most recent 100 messages per user

== Coming Soon ==

* Custom user templates
* BigQuery integration for aggregated editorial analytics
* A/B testing framework for prompt variants

----
''Righting Sentences is developed by Saxton Publishing.''

[[Category:Righting Sentences]]
[[Category:Release Notes]]

Righting Sentences Release Notes - 4.0

2026-02-06T19:29:05Z

Saxtonmd77: /* Conversation Export */

= Righting Sentences v4.0 Release Notes =

'''Release Date:''' 6 February 2026

'''Production URL:''' https://righting-sentences-573737403792.us-east1.run.app/

== Overview ==

Righting Sentences v4.0 includes content creation tools with Prompt Templates and Quick Actions, along with an Editorial Insights dashboard that shows how the two-pass editorial system improves writing. This release also adds the ability to export conversations in some file formats.

== Highlights ==

=== Prompt Templates ===
Pre-built templates for professional content creation, optimized for B2B marketing use cases.

'''Landing Page Templates:'''
* '''Locations''' - Creates pages for global offices and delivery centers
* '''Services''' - Builds pages for the overview of services
* '''Industries''' - Generates pages for industries or specializations
* '''Leadership''' - Drafts pages for leadership team members
* '''Clients''' - Creates a client portfolio

'''Case Study Templates:'''
* '''Case Study (PPT)''' - Single-page PPT
* '''Case Study (Website)''' - SEO-optimized web case study with KPIs

All templates use Google Gemini.

=== Quick Actions ===
Edit the previous response in one click:

* '''Make it shorter''' - Condenses content to approximately 50% of the original length
* '''Make it more formal''' - Increases professional tone
* '''Simplify this''' - Clarifie content
* '''Expand on this''' - Adds

Quick actions do not require additional prompts.

=== Editorial Insights ===
A new dashboard showing the user's editorial analytics:

* '''Total Messages''' - Number of messages processed through the editorial system
* '''Pass Rate''' - Percentage of AI responses that passed without violations
* '''Top Violations''' - Most common AI patterns detected in conversations
* '''Recent Corrections''' - Examples of recent system corrections

This feature helps users understand how the two-pass system works and which AI patterns are most commonly corrected from their prompts. However, the insights are not necessarily indicative of how the system is functioning as a whole.

=== Conversation Export ===
Export conversations for documentation or backup:

* '''Markdown format''' - For documentation
* '''JSON format''' - Structured data

== Technical Improvements ==

=== New Components ===
* <code>template_registry.py</code> - Template loading and resolution
* <code>editorial_insights.py</code> - Statistics computation (pure functions, no DB deps)
* <code>rate_limiter.py</code> - Request rate limiting
* <code>logging_config.py</code> - Structured logging configuration
* <code>InsightsPage.jsx</code> - Editorial insights UI component

=== Architecture ===
* Templates defined in <code>templates.md</code> for easy editing
* Template prompts inject into both Pass 1 and Pass 2 of the editorial system
* Quick actions automatically prepend context about the previous response
* Insights computed per-user from Firestore <code>editorial_logs</code> collection

=== Testing Infrastructure ===
* pytest configuration for backend tests
* Vitest setup for frontend component testing
* Development dependencies separated into <code>requirements-dev.txt</code>

== Upgrade Notes ==

=== For Users ===
No action required. New features are available immediately after deployment.

=== For Administrators ===
* The <code>/templates</code> endpoint is now available for template listing
* The <code>/insights</code> endpoint returns per-user editorial statistics
* Template-based requests automatically use Gemini regardless of selected model

== Known Limitations ==

* Templates are currently read-only (no custom template creation yet)
* Quick actions require at least one previous assistant message in the conversation
* Editorial insights are limited to the most recent 100 messages per user

== Coming Soon ==

* Custom user templates
* BigQuery integration for aggregated editorial analytics
* A/B testing framework for prompt variants

----
''Righting Sentences is developed by Saxton Publishing.''

[[Category:Righting Sentences]]
[[Category:Release Notes]]

Righting Sentences Release Notes - 4.0

2026-02-06T19:28:31Z

Saxtonmd77: /* Editorial Insights */

= Righting Sentences v4.0 Release Notes =

'''Release Date:''' 6 February 2026

'''Production URL:''' https://righting-sentences-573737403792.us-east1.run.app/

== Overview ==

Righting Sentences v4.0 includes content creation tools with Prompt Templates and Quick Actions, along with an Editorial Insights dashboard that shows how the two-pass editorial system improves writing. This release also adds the ability to export conversations in some file formats.

== Highlights ==

=== Prompt Templates ===
Pre-built templates for professional content creation, optimized for B2B marketing use cases.

'''Landing Page Templates:'''
* '''Locations''' - Creates pages for global offices and delivery centers
* '''Services''' - Builds pages for the overview of services
* '''Industries''' - Generates pages for industries or specializations
* '''Leadership''' - Drafts pages for leadership team members
* '''Clients''' - Creates a client portfolio

'''Case Study Templates:'''
* '''Case Study (PPT)''' - Single-page PPT
* '''Case Study (Website)''' - SEO-optimized web case study with KPIs

All templates use Google Gemini.

=== Quick Actions ===
Edit the previous response in one click:

* '''Make it shorter''' - Condenses content to approximately 50% of the original length
* '''Make it more formal''' - Increases professional tone
* '''Simplify this''' - Clarifie content
* '''Expand on this''' - Adds

Quick actions do not require additional prompts.

=== Editorial Insights ===
A new dashboard showing the user's editorial analytics:

* '''Total Messages''' - Number of messages processed through the editorial system
* '''Pass Rate''' - Percentage of AI responses that passed without violations
* '''Top Violations''' - Most common AI patterns detected in conversations
* '''Recent Corrections''' - Examples of recent system corrections

This feature helps users understand how the two-pass system works and which AI patterns are most commonly corrected from their prompts. However, the insights are not necessarily indicative of how the system is functioning as a whole.

=== Conversation Export ===
Export your conversations for documentation or backup:

* '''Markdown format''' - Clean, formatted text suitable for documentation
* '''JSON format''' - Structured data for programmatic use or archival

== Technical Improvements ==

=== New Components ===
* <code>template_registry.py</code> - Template loading and resolution
* <code>editorial_insights.py</code> - Statistics computation (pure functions, no DB deps)
* <code>rate_limiter.py</code> - Request rate limiting
* <code>logging_config.py</code> - Structured logging configuration
* <code>InsightsPage.jsx</code> - Editorial insights UI component

=== Architecture ===
* Templates defined in <code>templates.md</code> for easy editing
* Template prompts inject into both Pass 1 and Pass 2 of the editorial system
* Quick actions automatically prepend context about the previous response
* Insights computed per-user from Firestore <code>editorial_logs</code> collection

=== Testing Infrastructure ===
* pytest configuration for backend tests
* Vitest setup for frontend component testing
* Development dependencies separated into <code>requirements-dev.txt</code>

== Upgrade Notes ==

=== For Users ===
No action required. New features are available immediately after deployment.

=== For Administrators ===
* The <code>/templates</code> endpoint is now available for template listing
* The <code>/insights</code> endpoint returns per-user editorial statistics
* Template-based requests automatically use Gemini regardless of selected model

== Known Limitations ==

* Templates are currently read-only (no custom template creation yet)
* Quick actions require at least one previous assistant message in the conversation
* Editorial insights are limited to the most recent 100 messages per user

== Coming Soon ==

* Custom user templates
* BigQuery integration for aggregated editorial analytics
* A/B testing framework for prompt variants

----
''Righting Sentences is developed by Saxton Publishing.''

[[Category:Righting Sentences]]
[[Category:Release Notes]]

Righting Sentences Release Notes - 4.0

2026-02-06T19:21:16Z

Saxtonmd77: /* Quick Actions */

= Righting Sentences v4.0 Release Notes =

'''Release Date:''' 6 February 2026

'''Production URL:''' https://righting-sentences-573737403792.us-east1.run.app/

== Overview ==

Righting Sentences v4.0 includes content creation tools with Prompt Templates and Quick Actions, along with an Editorial Insights dashboard that shows how the two-pass editorial system improves writing. This release also adds the ability to export conversations in some file formats.

== Highlights ==

=== Prompt Templates ===
Pre-built templates for professional content creation, optimized for B2B marketing use cases.

'''Landing Page Templates:'''
* '''Locations''' - Creates pages for global offices and delivery centers
* '''Services''' - Builds pages for the overview of services
* '''Industries''' - Generates pages for industries or specializations
* '''Leadership''' - Drafts pages for leadership team members
* '''Clients''' - Creates a client portfolio

'''Case Study Templates:'''
* '''Case Study (PPT)''' - Single-page PPT
* '''Case Study (Website)''' - SEO-optimized web case study with KPIs

All templates use Google Gemini.

=== Quick Actions ===
Edit the previous response in one click:

* '''Make it shorter''' - Condenses content to approximately 50% of the original length
* '''Make it more formal''' - Increases professional tone
* '''Simplify this''' - Clarifie content
* '''Expand on this''' - Adds

Quick actions do not require additional prompts.

=== Editorial Insights ===
A new dashboard showing your personal editorial analytics:

* '''Total Messages''' - Number of messages processed through the editorial system
* '''Pass Rate''' - Percentage of AI responses that passed without violations
* '''Top Violations''' - Most common AI patterns detected in your conversations
* '''Recent Corrections''' - Examples of recent editorial improvements

This feature helps users understand how the two-pass system works and which AI patterns are most commonly corrected.

=== Conversation Export ===
Export your conversations for documentation or backup:

* '''Markdown format''' - Clean, formatted text suitable for documentation
* '''JSON format''' - Structured data for programmatic use or archival

== Technical Improvements ==

=== New Components ===
* <code>template_registry.py</code> - Template loading and resolution
* <code>editorial_insights.py</code> - Statistics computation (pure functions, no DB deps)
* <code>rate_limiter.py</code> - Request rate limiting
* <code>logging_config.py</code> - Structured logging configuration
* <code>InsightsPage.jsx</code> - Editorial insights UI component

=== Architecture ===
* Templates defined in <code>templates.md</code> for easy editing
* Template prompts inject into both Pass 1 and Pass 2 of the editorial system
* Quick actions automatically prepend context about the previous response
* Insights computed per-user from Firestore <code>editorial_logs</code> collection

=== Testing Infrastructure ===
* pytest configuration for backend tests
* Vitest setup for frontend component testing
* Development dependencies separated into <code>requirements-dev.txt</code>

== Upgrade Notes ==

=== For Users ===
No action required. New features are available immediately after deployment.

=== For Administrators ===
* The <code>/templates</code> endpoint is now available for template listing
* The <code>/insights</code> endpoint returns per-user editorial statistics
* Template-based requests automatically use Gemini regardless of selected model

== Known Limitations ==

* Templates are currently read-only (no custom template creation yet)
* Quick actions require at least one previous assistant message in the conversation
* Editorial insights are limited to the most recent 100 messages per user

== Coming Soon ==

* Custom user templates
* BigQuery integration for aggregated editorial analytics
* A/B testing framework for prompt variants

----
''Righting Sentences is developed by Saxton Publishing.''

[[Category:Righting Sentences]]
[[Category:Release Notes]]

Righting Sentences Release Notes - 4.0

2026-02-06T19:19:38Z

Saxtonmd77: /* Prompt Templates */

= Righting Sentences v4.0 Release Notes =

'''Release Date:''' 6 February 2026

'''Production URL:''' https://righting-sentences-573737403792.us-east1.run.app/

== Overview ==

Righting Sentences v4.0 includes content creation tools with Prompt Templates and Quick Actions, along with an Editorial Insights dashboard that shows how the two-pass editorial system improves writing. This release also adds the ability to export conversations in some file formats.

== Highlights ==

=== Prompt Templates ===
Pre-built templates for professional content creation, optimized for B2B marketing use cases.

'''Landing Page Templates:'''
* '''Locations''' - Creates pages for global offices and delivery centers
* '''Services''' - Builds pages for the overview of services
* '''Industries''' - Generates pages for industries or specializations
* '''Leadership''' - Drafts pages for leadership team members
* '''Clients''' - Creates a client portfolio

'''Case Study Templates:'''
* '''Case Study (PPT)''' - Single-page PPT
* '''Case Study (Website)''' - SEO-optimized web case study with KPIs

All templates use Google Gemini.

=== Quick Actions ===
One-click text transformations that work on the previous AI response:

* '''Make it shorter''' - Condense content to approximately 50% of original length
* '''Make it more formal''' - Increase professional tone and sophistication
* '''Simplify this''' - Make content clearer and more accessible
* '''Expand on this''' - Add detail, examples, and elaboration

Quick actions execute immediately without requiring additional user input.

=== Editorial Insights ===
A new dashboard showing your personal editorial analytics:

* '''Total Messages''' - Number of messages processed through the editorial system
* '''Pass Rate''' - Percentage of AI responses that passed without violations
* '''Top Violations''' - Most common AI patterns detected in your conversations
* '''Recent Corrections''' - Examples of recent editorial improvements

This feature helps users understand how the two-pass system works and which AI patterns are most commonly corrected.

=== Conversation Export ===
Export your conversations for documentation or backup:

* '''Markdown format''' - Clean, formatted text suitable for documentation
* '''JSON format''' - Structured data for programmatic use or archival

== Technical Improvements ==

=== New Components ===
* <code>template_registry.py</code> - Template loading and resolution
* <code>editorial_insights.py</code> - Statistics computation (pure functions, no DB deps)
* <code>rate_limiter.py</code> - Request rate limiting
* <code>logging_config.py</code> - Structured logging configuration
* <code>InsightsPage.jsx</code> - Editorial insights UI component

=== Architecture ===
* Templates defined in <code>templates.md</code> for easy editing
* Template prompts inject into both Pass 1 and Pass 2 of the editorial system
* Quick actions automatically prepend context about the previous response
* Insights computed per-user from Firestore <code>editorial_logs</code> collection

=== Testing Infrastructure ===
* pytest configuration for backend tests
* Vitest setup for frontend component testing
* Development dependencies separated into <code>requirements-dev.txt</code>

== Upgrade Notes ==

=== For Users ===
No action required. New features are available immediately after deployment.

=== For Administrators ===
* The <code>/templates</code> endpoint is now available for template listing
* The <code>/insights</code> endpoint returns per-user editorial statistics
* Template-based requests automatically use Gemini regardless of selected model

== Known Limitations ==

* Templates are currently read-only (no custom template creation yet)
* Quick actions require at least one previous assistant message in the conversation
* Editorial insights are limited to the most recent 100 messages per user

== Coming Soon ==

* Custom user templates
* BigQuery integration for aggregated editorial analytics
* A/B testing framework for prompt variants

----
''Righting Sentences is developed by Saxton Publishing.''

[[Category:Righting Sentences]]
[[Category:Release Notes]]

Righting Sentences Release Notes - 4.0

2026-02-06T19:16:39Z

Saxtonmd77: /* Overview */

= Righting Sentences v4.0 Release Notes =

'''Release Date:''' 6 February 2026

'''Production URL:''' https://righting-sentences-573737403792.us-east1.run.app/

== Overview ==

Righting Sentences v4.0 includes content creation tools with Prompt Templates and Quick Actions, along with an Editorial Insights dashboard that shows how the two-pass editorial system improves writing. This release also adds the ability to export conversations in some file formats.

== Highlights ==

=== Prompt Templates ===
Pre-built templates for professional content creation, optimized for B2B marketing use cases.

'''Landing Page Templates:'''
* '''Locations''' - Create global offices and delivery centers pages with proper structure
* '''Services''' - Build service overview pages with capabilities, proof points, and outcomes
* '''Industries''' - Generate industry overview or specialization pages
* '''Leadership''' - Draft leadership team introductions that build credibility
* '''Clients''' - Create client portfolio pages with testimonials and case study links

'''Case Study Templates:'''
* '''Case Study (PPT)''' - 7-slide PowerPoint structure with speaker notes suggestions
* '''Case Study (Website)''' - SEO-optimized web case study with metrics and storytelling

All templates automatically use Google Gemini for optimal results and integrate seamlessly with the two-pass editorial system.

=== Quick Actions ===
One-click text transformations that work on the previous AI response:

* '''Make it shorter''' - Condense content to approximately 50% of original length
* '''Make it more formal''' - Increase professional tone and sophistication
* '''Simplify this''' - Make content clearer and more accessible
* '''Expand on this''' - Add detail, examples, and elaboration

Quick actions execute immediately without requiring additional user input.

=== Editorial Insights ===
A new dashboard showing your personal editorial analytics:

* '''Total Messages''' - Number of messages processed through the editorial system
* '''Pass Rate''' - Percentage of AI responses that passed without violations
* '''Top Violations''' - Most common AI patterns detected in your conversations
* '''Recent Corrections''' - Examples of recent editorial improvements

This feature helps users understand how the two-pass system works and which AI patterns are most commonly corrected.

=== Conversation Export ===
Export your conversations for documentation or backup:

* '''Markdown format''' - Clean, formatted text suitable for documentation
* '''JSON format''' - Structured data for programmatic use or archival

== Technical Improvements ==

=== New Components ===
* <code>template_registry.py</code> - Template loading and resolution
* <code>editorial_insights.py</code> - Statistics computation (pure functions, no DB deps)
* <code>rate_limiter.py</code> - Request rate limiting
* <code>logging_config.py</code> - Structured logging configuration
* <code>InsightsPage.jsx</code> - Editorial insights UI component

=== Architecture ===
* Templates defined in <code>templates.md</code> for easy editing
* Template prompts inject into both Pass 1 and Pass 2 of the editorial system
* Quick actions automatically prepend context about the previous response
* Insights computed per-user from Firestore <code>editorial_logs</code> collection

=== Testing Infrastructure ===
* pytest configuration for backend tests
* Vitest setup for frontend component testing
* Development dependencies separated into <code>requirements-dev.txt</code>

== Upgrade Notes ==

=== For Users ===
No action required. New features are available immediately after deployment.

=== For Administrators ===
* The <code>/templates</code> endpoint is now available for template listing
* The <code>/insights</code> endpoint returns per-user editorial statistics
* Template-based requests automatically use Gemini regardless of selected model

== Known Limitations ==

* Templates are currently read-only (no custom template creation yet)
* Quick actions require at least one previous assistant message in the conversation
* Editorial insights are limited to the most recent 100 messages per user

== Coming Soon ==

* Custom user templates
* BigQuery integration for aggregated editorial analytics
* A/B testing framework for prompt variants

----
''Righting Sentences is developed by Saxton Publishing.''

[[Category:Righting Sentences]]
[[Category:Release Notes]]

Righting Sentences Release Notes - 4.0

2026-02-06T17:51:10Z

Saxtonmd77:

= Righting Sentences v4.0 Release Notes =

'''Release Date:''' 6 February 2026

'''Production URL:''' https://righting-sentences-573737403792.us-east1.run.app/

== Overview ==

Righting Sentences v4.0 introduces powerful content creation tools with Prompt Templates and Quick Actions, along with an Editorial Insights dashboard that gives users visibility into how the two-pass editorial system improves their writing. This release also adds conversation export capabilities.

== Highlights ==

=== Prompt Templates ===
Pre-built templates for professional content creation, optimized for B2B marketing use cases.

'''Landing Page Templates:'''
* '''Locations''' - Create global offices and delivery centers pages with proper structure
* '''Services''' - Build service overview pages with capabilities, proof points, and outcomes
* '''Industries''' - Generate industry overview or specialization pages
* '''Leadership''' - Draft leadership team introductions that build credibility
* '''Clients''' - Create client portfolio pages with testimonials and case study links

'''Case Study Templates:'''
* '''Case Study (PPT)''' - 7-slide PowerPoint structure with speaker notes suggestions
* '''Case Study (Website)''' - SEO-optimized web case study with metrics and storytelling

All templates automatically use Google Gemini for optimal results and integrate seamlessly with the two-pass editorial system.

=== Quick Actions ===
One-click text transformations that work on the previous AI response:

* '''Make it shorter''' - Condense content to approximately 50% of original length
* '''Make it more formal''' - Increase professional tone and sophistication
* '''Simplify this''' - Make content clearer and more accessible
* '''Expand on this''' - Add detail, examples, and elaboration

Quick actions execute immediately without requiring additional user input.

=== Editorial Insights ===
A new dashboard showing your personal editorial analytics:

* '''Total Messages''' - Number of messages processed through the editorial system
* '''Pass Rate''' - Percentage of AI responses that passed without violations
* '''Top Violations''' - Most common AI patterns detected in your conversations
* '''Recent Corrections''' - Examples of recent editorial improvements

This feature helps users understand how the two-pass system works and which AI patterns are most commonly corrected.

=== Conversation Export ===
Export your conversations for documentation or backup:

* '''Markdown format''' - Clean, formatted text suitable for documentation
* '''JSON format''' - Structured data for programmatic use or archival

== Technical Improvements ==

=== New Components ===
* <code>template_registry.py</code> - Template loading and resolution
* <code>editorial_insights.py</code> - Statistics computation (pure functions, no DB deps)
* <code>rate_limiter.py</code> - Request rate limiting
* <code>logging_config.py</code> - Structured logging configuration
* <code>InsightsPage.jsx</code> - Editorial insights UI component

=== Architecture ===
* Templates defined in <code>templates.md</code> for easy editing
* Template prompts inject into both Pass 1 and Pass 2 of the editorial system
* Quick actions automatically prepend context about the previous response
* Insights computed per-user from Firestore <code>editorial_logs</code> collection

=== Testing Infrastructure ===
* pytest configuration for backend tests
* Vitest setup for frontend component testing
* Development dependencies separated into <code>requirements-dev.txt</code>

== Upgrade Notes ==

=== For Users ===
No action required. New features are available immediately after deployment.

=== For Administrators ===
* The <code>/templates</code> endpoint is now available for template listing
* The <code>/insights</code> endpoint returns per-user editorial statistics
* Template-based requests automatically use Gemini regardless of selected model

== Known Limitations ==

* Templates are currently read-only (no custom template creation yet)
* Quick actions require at least one previous assistant message in the conversation
* Editorial insights are limited to the most recent 100 messages per user

== Coming Soon ==

* Custom user templates
* BigQuery integration for aggregated editorial analytics
* A/B testing framework for prompt variants

----
''Righting Sentences is developed by Saxton Publishing.''

[[Category:Righting Sentences]]
[[Category:Release Notes]]

Righting Sentences Release Notes - 4.0

2026-02-06T17:50:18Z

Saxtonmd77: Created page with "= Righting Sentences v4.0 Release Notes = '''Release Date:''' February 2026 '''Production URL:''' https://righting-sentences-573737403792.us-east1.run.app/ == Overview == Righting Sentences v4.0 introduces powerful content creation tools with Prompt Templates and Quick Actions, along with an Editorial Insights dashboard that gives users visibility into how the two-pass editorial system improves their writing. This release also adds conversation export capabilities...."

= Righting Sentences v4.0 Release Notes =

'''Release Date:''' February 2026

'''Production URL:''' https://righting-sentences-573737403792.us-east1.run.app/

== Overview ==

Righting Sentences v4.0 introduces powerful content creation tools with Prompt Templates and Quick Actions, along with an Editorial Insights dashboard that gives users visibility into how the two-pass editorial system improves their writing. This release also adds conversation export capabilities.

== Highlights ==

=== Prompt Templates ===
Pre-built templates for professional content creation, optimized for B2B marketing use cases.

'''Landing Page Templates:'''
* '''Locations''' - Create global offices and delivery centers pages with proper structure
* '''Services''' - Build service overview pages with capabilities, proof points, and outcomes
* '''Industries''' - Generate industry overview or specialization pages
* '''Leadership''' - Draft leadership team introductions that build credibility
* '''Clients''' - Create client portfolio pages with testimonials and case study links

'''Case Study Templates:'''
* '''Case Study (PPT)''' - 7-slide PowerPoint structure with speaker notes suggestions
* '''Case Study (Website)''' - SEO-optimized web case study with metrics and storytelling

All templates automatically use Google Gemini for optimal results and integrate seamlessly with the two-pass editorial system.

=== Quick Actions ===
One-click text transformations that work on the previous AI response:

* '''Make it shorter''' - Condense content to approximately 50% of original length
* '''Make it more formal''' - Increase professional tone and sophistication
* '''Simplify this''' - Make content clearer and more accessible
* '''Expand on this''' - Add detail, examples, and elaboration

Quick actions execute immediately without requiring additional user input.

=== Editorial Insights ===
A new dashboard showing your personal editorial analytics:

* '''Total Messages''' - Number of messages processed through the editorial system
* '''Pass Rate''' - Percentage of AI responses that passed without violations
* '''Top Violations''' - Most common AI patterns detected in your conversations
* '''Recent Corrections''' - Examples of recent editorial improvements

This feature helps users understand how the two-pass system works and which AI patterns are most commonly corrected.

=== Conversation Export ===
Export your conversations for documentation or backup:

* '''Markdown format''' - Clean, formatted text suitable for documentation
* '''JSON format''' - Structured data for programmatic use or archival

== Technical Improvements ==

=== New Components ===
* <code>template_registry.py</code> - Template loading and resolution
* <code>editorial_insights.py</code> - Statistics computation (pure functions, no DB deps)
* <code>rate_limiter.py</code> - Request rate limiting
* <code>logging_config.py</code> - Structured logging configuration
* <code>InsightsPage.jsx</code> - Editorial insights UI component

=== Architecture ===
* Templates defined in <code>templates.md</code> for easy editing
* Template prompts inject into both Pass 1 and Pass 2 of the editorial system
* Quick actions automatically prepend context about the previous response
* Insights computed per-user from Firestore <code>editorial_logs</code> collection

=== Testing Infrastructure ===
* pytest configuration for backend tests
* Vitest setup for frontend component testing
* Development dependencies separated into <code>requirements-dev.txt</code>

== Upgrade Notes ==

=== For Users ===
No action required. New features are available immediately after deployment.

=== For Administrators ===
* The <code>/templates</code> endpoint is now available for template listing
* The <code>/insights</code> endpoint returns per-user editorial statistics
* Template-based requests automatically use Gemini regardless of selected model

== Known Limitations ==

* Templates are currently read-only (no custom template creation yet)
* Quick actions require at least one previous assistant message in the conversation
* Editorial insights are limited to the most recent 100 messages per user

== Coming Soon ==

* Custom user templates
* BigQuery integration for aggregated editorial analytics
* A/B testing framework for prompt variants

----
''Righting Sentences is developed by Saxton Publishing.''

[[Category:Righting Sentences]]
[[Category:Release Notes]]

Righting Sentences User Guide - 4.0

2026-02-06T17:49:32Z

Saxtonmd77: Created page with "'''Righting Sentences''' — User Guide (v4.0) Last updated: February 2026 Production URL: https://righting-sentences-573737403792.us-east1.run.app/ __TOC__ == 1. Purpose and Scope == '''Righting Sentences''' is a web-based chat application that helps you write and revise text in standard written English using modern generative AI (GenAI) models. The application features a unique '''two-pass editorial system''' that automatically detects and removes AI-typical langu..."

'''Righting Sentences''' — User Guide (v4.0)

Last updated: February 2026

Production URL: https://righting-sentences-573737403792.us-east1.run.app/

__TOC__

== 1. Purpose and Scope ==
'''Righting Sentences''' is a web-based chat application that helps you write and revise text in standard written English using modern generative AI (GenAI) models.

The application features a unique '''two-pass editorial system''' that automatically detects and removes AI-typical language patterns, producing text that sounds more natural and human-like.

This service is a '''data science''' project. Your usage helps improve editorial rules and model behavior over time.

=== 1.1 Who this is for ===
* You want help drafting, revising, or polishing writing
* You want alternative phrasings, summaries, or structured outputs (lists, outlines, tables)
* You want to discuss a document you upload (text, office files, PDFs, images)
* You need to create professional content like landing pages or case studies

=== 1.2 What this is not ===
* It is not a source of guaranteed factual truth
* It is not a substitute for professional advice (legal, medical, financial)

== 2. Access and Authentication ==

=== 2.1 Google account required ===
To use the application, you must sign in with a Google account.

=== 2.2 Invitation-only access ===
Access is provided by invitation. If you cannot sign in or do not see the application after signing in, contact the administrator (Saxton Publishing).

=== 2.3 Sign in ===
# Navigate to the production URL
# Select '''Sign in with Google'''
# Complete Google authentication
# After sign-in, you will see the main chat interface

== 3. User Interface ==

=== 3.1 Layout overview ===
The interface has two main areas:
* '''Left sidebar''' - Chat history, model selector, and menu
* '''Main chat window''' - Conversation view and message input

=== 3.2 Left Sidebar ===

==== Chat history list ====
Each row shows:
* The conversation title
* The model used for that conversation

To open a conversation, select it from the list.

==== Model selector ====
Choose which AI model to use for new conversations:
* '''GPT-4o''' - OpenAI's capable general-purpose model
* '''GPT-5.2 Pro''' - OpenAI's advanced reasoning model
* '''Claude Sonnet 4.5''' - Anthropic's balanced model
* '''Gemini-3 Flash''' - Google's fast, efficient model

'''Important:''' Models cannot be changed mid-conversation. Start a new chat to use a different model.

==== Menu items ====
* '''Account''' - View your profile and sign out
* '''Settings''' - Theme, colors, and custom instructions
* '''Insights''' - Editorial analytics dashboard
* '''Help''' - Link to documentation
* '''Sign Out''' - End your session

=== 3.3 Main Chat Window ===

==== Header ====
Shows the conversation title and current model badge.

==== Messages ====
* Your messages appear on the right
* Assistant messages appear on the left
* Hover over assistant messages to reveal the copy button

==== Message input ====
Type your message and press Enter or click Send.

== 4. Sending Messages ==

=== 4.1 Basic messaging ===
# Type your message in the input field
# Press '''Enter''' or click '''Send'''
# Wait for the assistant to respond

=== 4.2 Multi-line messages ===
Press '''Shift+Enter''' to create a new line without sending.

=== 4.3 Stop generation ===
While the assistant is responding, click '''Stop''' to halt generation early.

== 5. Options Menu ==

The '''Options''' button inside the message input provides access to:
* File uploads
* Prompt templates
* Quick actions

=== 5.1 Opening Options ===
Click the '''Options''' button (three dots icon) to reveal the dropdown menu.

== 6. File Uploads ==

=== 6.1 Upload a file ===
# Click '''Options'''
# Select '''Upload files'''
# Choose one or more files

=== 6.2 Supported file types ===
* '''Text:''' .txt, .md, .csv, .tsv, .json
* '''Documents:''' .pdf, .doc, .docx
* '''Presentations:''' .ppt, .pptx
* '''Spreadsheets:''' .xls, .xlsx
* '''Images:''' .png, .jpg, .gif, .webp, .bmp, .tiff

=== 6.3 File status ===
Uploaded files appear as chips above the input:
* '''Uploaded''' - File received
* '''Parsed''' - Text extracted and available to the model

=== 6.4 Remove a file ===
Click the '''×''' on the file chip to remove it from the conversation.

=== 6.5 File size limit ===
Maximum upload size is 25 MB per file.

== 7. Prompt Templates ==

Templates provide structured prompts for common content types.

=== 7.1 Using a template ===
# Click '''Options'''
# Select a template from the list
# The template badge appears above the input
# Type your specific content or context
# Send your message

=== 7.2 Available templates ===

==== Landing Pages ====
{| class="wikitable"
! Template !! Description
|-
| Locations || Global offices and delivery centers page
|-
| Services || Service overview with capabilities, proof, and outcomes
|-
| Industries || Industry overview or specialization page
|-
| Leadership || Leadership team introduction and credibility
|-
| Clients || Client portfolio and proof of impact
|}

==== Case Studies ====
{| class="wikitable"
! Template !! Description
|-
| Case Study (PPT) || PowerPoint presentation structure (7 slides)
|-
| Case Study (Website) || Web-optimized case study with metrics
|}

=== 7.3 Template behavior ===
* Templates automatically use '''Google Gemini''' for optimal results
* The template badge shows which template is active
* Click '''×''' on the badge to clear the template

== 8. Quick Actions ==

Quick actions transform the previous AI response with one click.

=== 8.1 Available quick actions ===
{| class="wikitable"
! Action !! Effect
|-
| Make it shorter || Condense to ~50% of original length
|-
| Make it more formal || Increase professional tone
|-
| Simplify this || Make clearer and more accessible
|-
| Expand on this || Add detail and elaboration
|}

=== 8.2 Using quick actions ===
# Ensure there is a previous assistant message in the conversation
# Click '''Options'''
# Select a quick action
# The action executes immediately (no additional prompt needed)

=== 8.3 Quick action behavior ===
* Quick actions automatically reference the previous assistant response
* They use '''Google Gemini''' regardless of conversation model
* The transformed response appears as a new message

== 9. Editorial Insights ==

The Insights dashboard shows your personal editorial analytics.

=== 9.1 Accessing Insights ===
# Open the sidebar
# Click '''Insights''' in the menu

=== 9.2 Metrics displayed ===
* '''Total Messages''' - Number of messages processed
* '''Passed''' - Messages without AI pattern violations
* '''Violations''' - Messages where patterns were detected and corrected
* '''Pass Rate''' - Percentage of clean messages

=== 9.3 Top Violations ===
Shows the most common AI-typical words detected in your conversations, such as:
* "utilize" (instead of "use")
* "landscape" (overused in AI writing)
* "delve" (AI favorite)

=== 9.4 Recent Corrections ===
Examples of recent messages where the editorial system improved the output.

== 10. Conversation Export ==

Export your conversations for documentation or backup.

=== 10.1 Export formats ===
* '''Markdown''' - Formatted text file
* '''JSON''' - Structured data

=== 10.2 How to export ===
# Open the conversation you want to export
# Click the '''Export''' button in the header
# Select '''Markdown''' or '''JSON'''
# The file downloads automatically

== 11. Settings ==

=== 11.1 Theme ===
* '''Light''' - Light background
* '''Dark''' - Dark background
* '''System''' - Match your operating system preference

=== 11.2 Primary color ===
Choose an accent color for buttons and highlights.

=== 11.3 Custom instructions ===
Provide information about your preferences that the assistant should remember.

=== 11.4 LLM instructions ===
Add rules for how the assistant should respond in all conversations.

== 12. The Two-Pass Editorial System ==

Righting Sentences uses a unique two-pass system to improve AI output.

=== 12.1 How it works ===
# '''Pass 1:''' The AI generates a natural response
# '''Detection:''' The system identifies AI-typical patterns:
#* Banned words (e.g., "utilize", "landscape", "delve")
#* Three-part lists (triads)
#* Rhetorical patterns (e.g., "It's not X, it's Y")
# '''Pass 2:''' The AI regenerates with stricter guidelines
# '''Post-processing:''' Any remaining issues are cleaned programmatically

=== 12.2 Why it matters ===
AI models tend to overuse certain words and patterns that make text sound artificial. The editorial system produces writing that sounds more natural and human-like.

=== 12.3 Banned words ===
The system currently flags: utilize, landscape, unlock, critical, guardrails, tracks, shape, shift, teams, delve, tapestry.

=== 12.4 Triad exceptions ===
Some three-part phrases are culturally significant and exempt from editing:
* "executive, legislative, and judicial"
* "life, liberty, and the pursuit of happiness"
* "red, white, and blue"

== 13. Troubleshooting ==

=== 13.1 I cannot sign in ===
* Confirm you are using a Google account
* Confirm your account has been invited
* Contact Saxton Publishing if the problem persists

=== 13.2 I cannot change the model ===
Models cannot be changed mid-conversation. Start a new chat to use a different model.

=== 13.3 Quick actions are not available ===
Quick actions require at least one assistant message in the conversation. Send a message first, then use quick actions.

=== 13.4 Template is not working ===
* Ensure the template badge is visible above the input
* Templates require you to provide context in your message
* If issues persist, clear the template and try again

=== 13.5 File upload fails ===
* Check that the file is under 25 MB
* Verify the file type is supported
* Contact the administrator if errors persist

== 14. Data and Privacy ==

=== 14.1 What is stored ===
* Conversations and messages
* Uploaded files
* Editorial logs (for system improvement)

=== 14.2 Where data is stored ===
* Google Cloud Firestore (conversations, metadata)
* Google Cloud Storage (uploaded files)

=== 14.3 Third-party providers ===
Messages are sent to the selected model provider (OpenAI, Anthropic, or Google) to generate responses.

----
''Righting Sentences is developed by Saxton Publishing.''

[[Category:Righting Sentences]]
[[Category:User Guide]]

Righting Sentences Changelog - 3.2-4.0

2026-02-06T17:42:05Z

Saxtonmd77: Created page with "= Righting Sentences Changelog: v3.2 to v4.0 = '''Comprehensive list of changes from version 3.2.0 to 4.0.0''' == Version 4.0.0 (February 2026) == === New Features === ==== Prompt Templates ==== * Added template system for structured content generation * '''Landing Page Templates:''' ** Locations - Global offices and delivery centers ** Services - Service overview with capabilities, proof, and outcomes ** Industries - Industry overview or specialization pages ** Lead..."

= Righting Sentences Changelog: v3.2 to v4.0 =

'''Comprehensive list of changes from version 3.2.0 to 4.0.0'''

== Version 4.0.0 (February 2026) ==

=== New Features ===

==== Prompt Templates ====
* Added template system for structured content generation
* '''Landing Page Templates:'''
** Locations - Global offices and delivery centers
** Services - Service overview with capabilities, proof, and outcomes
** Industries - Industry overview or specialization pages
** Leadership - Team introduction and credibility pages
** Clients - Client portfolio and proof of impact
* '''Case Study Templates:'''
** Case Study (PPT) - PowerPoint presentation structure
** Case Study (Website) - Web-optimized case study format
* All templates automatically use Google Gemini model for optimal results
* Template prompt injection into two-pass editorial system

==== Quick Actions ====
* One-click text transformations that auto-execute
* Four built-in quick actions:
** ''Make it shorter'' - Condense responses to ~50% length
** ''Make it more formal'' - Increase professional tone
** ''Simplify this'' - Make content clearer and more accessible
** ''Expand on this'' - Add detail and elaboration
* Quick actions automatically reference the previous AI response
* No user prompt required - executes immediately on selection

==== Editorial Insights Dashboard ====
* New "Insights" section accessible from sidebar menu
* Per-user analytics on editorial system performance
* Metrics displayed:
** Total messages analyzed
** Pass count (messages without violations)
** Fail count (messages with violations detected)
** Pass rate percentage
* Top violations chart showing most common AI patterns detected
* Recent corrections log showing specific examples

==== Conversation Export ====
* Export conversations in multiple formats:
** Markdown (.md) - Formatted for documentation
** JSON - Structured data for programmatic use
* Export button in chat header
* Preserves full conversation history including model information

==== Options Dropdown ====
* Redesigned message input interface
* Unified "Options" dropdown inside input field containing:
** File upload
** Template selection (organized by category)
** Quick actions
* Cleaner, more compact input area

=== Improvements ===

==== Backend ====
* New <code>template_registry.py</code> module for template management
* Template definitions stored in <code>templates.md</code> for easy editing
* <code>editorial_insights.py</code> module for statistics computation
* Pure function design for testability (no database dependencies in compute)
* Rate limiter module (<code>rate_limiter.py</code>)
* Structured logging configuration (<code>logging_config.py</code>)
* Preferences API endpoint for editorial insights

==== Frontend ====
* <code>InsightsPage.jsx</code> component for analytics display
* Updated <code>MessageInput.jsx</code> with Options dropdown
* Template state management in App.jsx
* Auto-send functionality for quick actions

==== Infrastructure ====
* Added <code>pytest.ini</code> for test configuration
* Added <code>requirements-dev.txt</code> for development dependencies
* Test directory structure (<code>tests/</code>)
* Frontend testing setup with Vitest

=== Bug Fixes ===
* Fixed OAuth cookie handling for improved session reliability (from v3.3.0)
* Resolved package-lock.json version synchronization issues

== Version 3.3.0 (January 2026) ==

=== Features ===
* OAuth cookie fallback mechanism for improved authentication reliability
* Enhanced prompt engineering for more natural conversations

== Version 3.2.0 (January 2026) ==

=== Features ===
* Improved conversation style in system prompts
* More natural, engaging chat assistant personality
* Better handling of casual vs. formal tone

----
''Generated: February 2026''

[[Category:Righting Sentences]]
[[Category:Changelog]]

Main Page

2026-02-06T17:41:55Z

Saxtonmd77: /* Pages on this Site */

Writing and editing prompts

2026-02-01T20:36:23Z

Saxtonmd77:

== Landing Page Templates ==

Format:

* Each template starts with a "##" line using the template id.
* label and description are required.
* Everything after "prompt:" belongs to the prompt until the next "##".

=== ## locations ===

'''label:''' Locations

'''description:''' Global offices and delivery centers page.

'''prompt:'''

You are a senior B2B web strategist and copywriter.

1. Read the keyword list attached to this prompt.
2. Review attached Source Material.
3. Build a full Locations landing page based on the topic.
4. Ensure every keywords in the keyword list is in the output.
5. Mark all keywords in bold.
6. If any keywords are missing in the output, provide a list at the end.

Output format (Markdown) - use the exact headings and order below:

* Page title: "Locations"
* Section 1: "Headline / Intro" (global reach + unified delivery message)
* Section 2: "Global Scale Summary" (3-6 metrics with placeholders if unknown)
* Section 3: "Locations by Region" (group by region/country; include city, office type, contact placeholders)
* Section 4: "Main Contact" (single global contact block)
* Section 5: "Regional Links" (region-specific services/offerings)
* CTA block: "Contact via form or email" (include suggested button + email copy)

Constraints:

* Follow the exact section order and labels above
* Use Markdown H2 headings (##) with the exact section titles
* Do not add or remove sections
* Modern, credible, global tone
* Never add information that is not true
* Clear scannable sections and short paragraphs
* Use bracketed placeholders for unknown facts (example: [Number of engineers])

---

=== ## services ===

'''label:''' Services

'''description:''' Service overview page with capabilities, proof, and outcomes.

'''prompt:'''

You are a senior B2B web strategist and copywriter. The user message is the topic and context for this page (service name, domain, audience).

1. Read the keyword list attached to this prompt.
2. Review attached Source Material.
3. Build a full Services landing page based on the topic.
4. Ensure every keywords in the keyword list is in the output.
5. Mark all keywords in bold.
6. If any keywords are missing in the output, provide a list at the end.

Output format (Markdown) - use the exact headings and order below:

* Page title: "Services"
* Section 1: "Hero — Headline & Value Proposition (Mandatory)" (keep this section short; include a note for a page progress bar)
* Section 2: "Client Logos (Mandatory)" (logos row immediately after hero)
* Section 3: "Problem Statement / Why It Matters / Challenges We Solve (Mandatory)"
* Section 4: "What We Offer — Services / Capabilities / Deliverables (Mandatory)"
* Section 5: "Client Success Stories / Case Studies / Social Proof / Partnerships (Mandatory)" (multiple compact examples)
* Section 6: "Our Approach / How We Deliver Value (Optional)" (stage-by-stage, outcome-focused)
* Section 7: "Benefits & Value Outcomes (Optional)" (impact metrics and results)
* Section 8: "Differentiators / Why Choose Us (Optional)"
* Section 9: "Use Cases & Industry/Domain Examples (Optional)" (tab system)
* Section 10: "Expert Snapshot (Optional)" (short bios only)
* Section 11: "FAQs (Mandatory)"
* Section 12: "Related Content & Interlinks (Mandatory)"
* CTA block: "Contact via form or email"

Constraints:

* Follow the exact section order and labels above
* Use Markdown H2 headings (##) with the exact section titles
* Do not add or remove sections
* Use concise, outcome-focused copy
* Never add information that is not true
* Use bracketed placeholders for unknown facts

---

=== ## industries ===

'''label:''' Industrie

'''description:''' Industry overview or specialization page.

'''prompt:'''

You are a senior B2B web strategist and copywriter. Decide which level to use:

* If the topic is a broad industry (example: Retail, Mobility, Digital Health), use Level 1.
* If the topic is a sub-industry or specialization (example: Retail AI, Medical Devices, ADAS), use Level 2/3.

1. Read the keyword list attached to this prompt.
2. Review attached Source Material.
3. Build a full Industry landing page based on the topic.
4. Ensure every keywords in the keyword list is in the output.
5. Mark all keywords in bold.
6. If any keywords are missing in the output, provide a list at the end.

Output format (Markdown):

* Page title: "Industries"

If Level 1 (Industry Overview) use the exact headings and order below:

* Section 1: "Hero — Industry Value Proposition"
* Section 2: "Industry-Specific Capabilities Overview"
* Section 3: "Entry Points to Sub-Industry Pages"
* Section 4: "Representative Use Cases / Impact Examples"
* Section 5: "Social Proof + Client Logos"
* Section 6: "Curated Insights & Related Content"
* CTA block: "Contact via form or email"

If Level 2/3 (Specialization) use the exact headings and order below:

* Section 1: "Hero — Specialized Value Proposition"
* Section 2: "Specific Challenges / Problems Solved"
* Section 3: "Specialized Services & Capabilities"
* Section 4: "Detailed Approach — How We Deliver Value (Optional)"
* Section 5: "Use Cases (Tabbed)"
* Section 6: "Multiple Case Studies"
* Section 7: "Impact Numbers / Outcomes"
* Section 8: "Social Proof / Certifications / Partnerships"
* Section 9: "Related Pages & Parent Industry"
* CTA block: "Contact via form or email"

Constraints:

* Follow the exact section order and labels above for the chosen level
* Use Markdown H2 headings (##) with the exact section titles
* Do not add or remove sections
* Never add information that is not true
* Modern, industry-specific tone
* Use bracketed placeholders for unknown facts

---

=== ## leadership ===

'''label:''' Leadership

'''description:''' Leadership team introduction and credibility page.

'''prompt:'''

You are a senior B2B web strategist and copywriter.

1. Read the keyword list attached to this prompt.
2. Review attached Source Material.
3. Build a full Leadership landing page based on the topic.
4. Ensure every keywords in the keyword list is in the output.
5. Mark all keywords in bold.
6. If any keywords are missing in the output, provide a list at the end.

Output format (Markdown) - use the exact headings and order below:

* Page title: "Leadership"
* Section 1: "Headline / Intro"
* Section 2: "Team Overview"
* Section 3: "Leadership Bios"
* Section 4: "Values & Vision"
* Optional Section: "Who We Are (Merge Option)"
* CTA block: "Contact via form or email"

Constraints:

* Follow the exact section order and labels above
* Use Markdown H2 headings (##) with the exact section titles
* Do not add or remove sections (except optional merge block when relevant)
* Emphasize credibility, clarity, and trust
* Never add information that is not true
* Keep bios concise and scannable
* Use bracketed placeholders for unknown facts

---

=== ## clients ===

'''label:''' Clients

'''description:''' Client portfolio, logos, and proof of impact page.

'''prompt:'''

You are a senior B2B web strategist and copywriter.

1. Read the keyword list attached to this prompt.
2. Review attached Source Material.
3. Build a full Client landing page based on the topic.
4. Ensure every keywords in the keyword list is in the output.
5. Mark all keywords in bold.
6. If any keywords are missing in the output, provide a list at the end.

Output format (Markdown) - use the exact headings and order below:

* Page title: "Clients"
* Section 1: "Headline / Intro"
* Section 2: "Client Logos (Filtered by Industry)"
* Section 3: "Featured Case Studies" (include "See all case studies" link)
* Section 4: "Client Testimonials"
* Section 5: "Client Videos"
* Section 6: "Full Client List Access"
* CTA block: "Contact via form or email"

Constraints:

* Follow the exact section order and labels above
* Use Markdown H2 headings (##) with the exact section titles
* Do not add or remove sections
* Never add information that is not true
* Trust-first tone with concrete outcomes
* Use bracketed placeholders for unknown facts

Writing and editing prompts

2026-02-01T20:33:47Z

Saxtonmd77:

Here is the content converted into MediaWiki format for your documentation site.

== Landing Page Templates ==

Format:

* Each template starts with a "##" line using the template id.
* label and description are required.
* Everything after "prompt:" belongs to the prompt until the next "##".

=== ## locations ===

'''label:''' Locations
'''description:''' Global offices and delivery centers page.
'''prompt:'''
You are a senior B2B web strategist and copywriter for Intellias.

1. Read the keyword list attached to this prompt.
2. Review attached Source Material.
3. Build a full Locations landing page based on the topic.
4. Ensure every keywords in the keyword list is in the output.
5. Mark all keywords in bold.
6. If any keywords are missing in the output, provide a list at the end.

Output format (Markdown) - use the exact headings and order below:

* Page title: "Locations"
* Section 1: "Headline / Intro" (global reach + unified delivery message)
* Section 2: "Global Scale Summary" (3-6 metrics with placeholders if unknown)
* Section 3: "Locations by Region" (group by region/country; include city, office type, contact placeholders)
* Section 4: "Main Contact" (single global contact block)
* Section 5: "Regional Links" (region-specific services/offerings)
* CTA block: "Contact via form or email" (include suggested button + email copy)

Constraints:

* Follow the exact section order and labels above
* Use Markdown H2 headings (##) with the exact section titles
* Do not add or remove sections
* Modern, credible, global tone
* Never add information that is not true
* Clear scannable sections and short paragraphs
* Use bracketed placeholders for unknown facts (example: [Number of engineers])

---

=== ## services ===

'''label:''' Services
'''description:''' Service overview page with capabilities, proof, and outcomes.
'''prompt:'''
You are a senior B2B web strategist and copywriter. The user message is the topic and context for this page (service name, domain, audience).

1. Read the keyword list attached to this prompt.
2. Review attached Source Material.
3. Build a full Services landing page based on the topic.
4. Ensure every keywords in the keyword list is in the output.
5. Mark all keywords in bold.
6. If any keywords are missing in the output, provide a list at the end.

Output format (Markdown) - use the exact headings and order below:

* Page title: "Services"
* Section 1: "Hero — Headline & Value Proposition (Mandatory)" (keep this section short; include a note for a page progress bar)
* Section 2: "Client Logos (Mandatory)" (logos row immediately after hero)
* Section 3: "Problem Statement / Why It Matters / Challenges We Solve (Mandatory)"
* Section 4: "What We Offer — Services / Capabilities / Deliverables (Mandatory)"
* Section 5: "Client Success Stories / Case Studies / Social Proof / Partnerships (Mandatory)" (multiple compact examples)
* Section 6: "Our Approach / How We Deliver Value (Optional)" (stage-by-stage, outcome-focused)
* Section 7: "Benefits & Value Outcomes (Optional)" (impact metrics and results)
* Section 8: "Differentiators / Why Choose Us (Optional)"
* Section 9: "Use Cases & Industry/Domain Examples (Optional)" (tab system)
* Section 10: "Expert Snapshot (Optional)" (short bios only)
* Section 11: "FAQs (Mandatory)"
* Section 12: "Related Content & Interlinks (Mandatory)"
* CTA block: "Contact via form or email"

Constraints:

* Follow the exact section order and labels above
* Use Markdown H2 headings (##) with the exact section titles
* Do not add or remove sections
* Use concise, outcome-focused copy
* Never add information that is not true
* Use bracketed placeholders for unknown facts

---

=== ## industries ===

'''label:''' Industrie
'''description:''' Industry overview or specialization page.
'''prompt:'''
You are a senior B2B web strategist and copywriter. Decide which level to use:

* If the topic is a broad industry (example: Retail, Mobility, Digital Health), use Level 1.
* If the topic is a sub-industry or specialization (example: Retail AI, Medical Devices, ADAS), use Level 2/3.

1. Read the keyword list attached to this prompt.
2. Review attached Source Material.
3. Build a full Industry landing page based on the topic.
4. Ensure every keywords in the keyword list is in the output.
5. Mark all keywords in bold.
6. If any keywords are missing in the output, provide a list at the end.

Output format (Markdown):

* Page title: "Industries"

If Level 1 (Industry Overview) use the exact headings and order below:

* Section 1: "Hero — Industry Value Proposition"
* Section 2: "Industry-Specific Capabilities Overview"
* Section 3: "Entry Points to Sub-Industry Pages"
* Section 4: "Representative Use Cases / Impact Examples"
* Section 5: "Social Proof + Client Logos"
* Section 6: "Curated Insights & Related Content"
* CTA block: "Contact via form or email"

If Level 2/3 (Specialization) use the exact headings and order below:

* Section 1: "Hero — Specialized Value Proposition"
* Section 2: "Specific Challenges / Problems Solved"
* Section 3: "Specialized Services & Capabilities"
* Section 4: "Detailed Approach — How We Deliver Value (Optional)"
* Section 5: "Use Cases (Tabbed)"
* Section 6: "Multiple Case Studies"
* Section 7: "Impact Numbers / Outcomes"
* Section 8: "Social Proof / Certifications / Partnerships"
* Section 9: "Related Pages & Parent Industry"
* CTA block: "Contact via form or email"

Constraints:

* Follow the exact section order and labels above for the chosen level
* Use Markdown H2 headings (##) with the exact section titles
* Do not add or remove sections
* Never add information that is not true
* Modern, industry-specific tone
* Use bracketed placeholders for unknown facts

---

=== ## leadership ===

'''label:''' Leadership
'''description:''' Leadership team introduction and credibility page.
'''prompt:'''
You are a senior B2B web strategist and copywriter.

1. Read the keyword list attached to this prompt.
2. Review attached Source Material.
3. Build a full Leadership landing page based on the topic.
4. Ensure every keywords in the keyword list is in the output.
5. Mark all keywords in bold.
6. If any keywords are missing in the output, provide a list at the end.

Output format (Markdown) - use the exact headings and order below:

* Page title: "Leadership"
* Section 1: "Headline / Intro"
* Section 2: "Team Overview"
* Section 3: "Leadership Bios"
* Section 4: "Values & Vision"
* Optional Section: "Who We Are (Merge Option)"
* CTA block: "Contact via form or email"

Constraints:

* Follow the exact section order and labels above
* Use Markdown H2 headings (##) with the exact section titles
* Do not add or remove sections (except optional merge block when relevant)
* Emphasize credibility, clarity, and trust
* Never add information that is not true
* Keep bios concise and scannable
* Use bracketed placeholders for unknown facts

---

=== ## clients ===

'''label:''' Clients
'''description:''' Client portfolio, logos, and proof of impact page.
'''prompt:'''
You are a senior B2B web strategist and copywriter.

1. Read the keyword list attached to this prompt.
2. Review attached Source Material.
3. Build a full Client landing page based on the topic.
4. Ensure every keywords in the keyword list is in the output.
5. Mark all keywords in bold.
6. If any keywords are missing in the output, provide a list at the end.

Output format (Markdown) - use the exact headings and order below:

* Page title: "Clients"
* Section 1: "Headline / Intro"
* Section 2: "Client Logos (Filtered by Industry)"
* Section 3: "Featured Case Studies" (include "See all case studies" link)
* Section 4: "Client Testimonials"
* Section 5: "Client Videos"
* Section 6: "Full Client List Access"
* CTA block: "Contact via form or email"

Constraints:

* Follow the exact section order and labels above
* Use Markdown H2 headings (##) with the exact section titles
* Do not add or remove sections
* Never add information that is not true
* Trust-first tone with concrete outcomes
* Use bracketed placeholders for unknown facts

Writing and editing prompts

2026-02-01T20:30:46Z

Saxtonmd77:

#Landing Page Templates

Format:

- Each template starts with a "##" line using the template id.
- label and description are required.
- Everything after "prompt:" belongs to the prompt until the next "##".

## locations

label: Locations
description: Global offices and delivery centers page.
prompt:
You are a senior B2B web strategist and copywriter for Intellias.

1. Read the keyword list attached to this prompt.
2. Review attached Source Material.
3. Build a full Locations landing page based on the topic.
4. Ensure every keywords in the keyword list is in the output.
5. Mark all keywords in bold.
6. If any keywords are missing in the output, provide a list at the end.

Output format (Markdown) - use the exact headings and order below:

- Page title: "Locations"
- Section 1: "Headline / Intro" (global reach + unified delivery message)
- Section 2: "Global Scale Summary" (3-6 metrics with placeholders if unknown)
- Section 3: "Locations by Region" (group by region/country; include city, office type, contact placeholders)
- Section 4: "Main Contact" (single global contact block)
- Section 5: "Regional Links" (region-specific services/offerings)
- CTA block: "Contact via form or email" (include suggested button + email copy)

Constraints:

- Follow the exact section order and labels above
- Use Markdown H2 headings (##) with the exact section titles
- Do not add or remove sections
- Modern, credible, global tone
- Never add information that is not true
- Clear scannable sections and short paragraphs
- Use bracketed placeholders for unknown facts (example: [Number of engineers])

## services

label: Services
description: Service overview page with capabilities, proof, and outcomes.
prompt:
You are a senior B2B web strategist and copywriter. The user message is the topic and context for this page (service name, domain, audience).

1. Read the keyword list attached to this prompt.
2. Review attached Source Material.
3. Build a full Services landing page based on the topic.
4. Ensure every keywords in the keyword list is in the output.
5. Mark all keywords in bold.
6. If any keywords are missing in the output, provide a list at the end.

Output format (Markdown) - use the exact headings and order below:

- Page title: "Services"
- Section 1: "Hero — Headline & Value Proposition (Mandatory)" (keep this section short; include a note for a page progress bar)
- Section 2: "Client Logos (Mandatory)" (logos row immediately after hero)
- Section 3: "Problem Statement / Why It Matters / Challenges We Solve (Mandatory)"
- Section 4: "What We Offer — Services / Capabilities / Deliverables (Mandatory)"
- Section 5: "Client Success Stories / Case Studies / Social Proof / Partnerships (Mandatory)" (multiple compact examples)
- Section 6: "Our Approach / How We Deliver Value (Optional)" (stage-by-stage, outcome-focused)
- Section 7: "Benefits & Value Outcomes (Optional)" (impact metrics and results)
- Section 8: "Differentiators / Why Choose Us (Optional)"
- Section 9: "Use Cases & Industry/Domain Examples (Optional)" (tab system)
- Section 10: "Expert Snapshot (Optional)" (short bios only)
- Section 11: "FAQs (Mandatory)"
- Section 12: "Related Content & Interlinks (Mandatory)"
- CTA block: "Contact via form or email"

Constraints:

- Follow the exact section order and labels above
- Use Markdown H2 headings (##) with the exact section titles
- Do not add or remove sections
- Use concise, outcome-focused copy
- Never add information that is not true
- Use bracketed placeholders for unknown facts

## industries

label: Industrie
description: Industry overview or specialization page.
prompt:
You are a senior B2B web strategist and copywriter. Decide which level to use:

- If the topic is a broad industry (example: Retail, Mobility, Digital Health), use Level 1.
- If the topic is a sub-industry or specialization (example: Retail AI, Medical Devices, ADAS), use Level 2/3.

1. Read the keyword list attached to this prompt.
2. Review attached Source Material.
3. Build a full Industry landing page based on the topic.
4. Ensure every keywords in the keyword list is in the output.
5. Mark all keywords in bold.
6. If any keywords are missing in the output, provide a list at the end.

Output format (Markdown):

- Page title: "Industries"

If Level 1 (Industry Overview) use the exact headings and order below:

- Section 1: "Hero — Industry Value Proposition"
- Section 2: "Industry-Specific Capabilities Overview"
- Section 3: "Entry Points to Sub-Industry Pages"
- Section 4: "Representative Use Cases / Impact Examples"
- Section 5: "Social Proof + Client Logos"
- Section 6: "Curated Insights & Related Content"
- CTA block: "Contact via form or email"

If Level 2/3 (Specialization) use the exact headings and order below:

- Section 1: "Hero — Specialized Value Proposition"
- Section 2: "Specific Challenges / Problems Solved"
- Section 3: "Specialized Services & Capabilities"
- Section 4: "Detailed Approach — How We Deliver Value (Optional)"
- Section 5: "Use Cases (Tabbed)"
- Section 6: "Multiple Case Studies"
- Section 7: "Impact Numbers / Outcomes"
- Section 8: "Social Proof / Certifications / Partnerships"
- Section 9: "Related Pages & Parent Industry"
- CTA block: "Contact via form or email"

Constraints:

- Follow the exact section order and labels above for the chosen level
- Use Markdown H2 headings (##) with the exact section titles
- Do not add or remove sections
- Never add information that is not true
- Modern, industry-specific tone
- Use bracketed placeholders for unknown facts

## leadership

label: Leadership
description: Leadership team introduction and credibility page.
prompt:
You are a senior B2B web strategist and copywriter.

1. Read the keyword list attached to this prompt.
2. Review attached Source Material.
3. Build a full Leadership landing page based on the topic.
4. Ensure every keywords in the keyword list is in the output.
5. Mark all keywords in bold.
6. If any keywords are missing in the output, provide a list at the end.

Output format (Markdown) - use the exact headings and order below:

- Page title: "Leadership"
- Section 1: "Headline / Intro"
- Section 2: "Team Overview"
- Section 3: "Leadership Bios"
- Section 4: "Values & Vision"
- Optional Section: "Who We Are (Merge Option)"
- CTA block: "Contact via form or email"

Constraints:

- Follow the exact section order and labels above
- Use Markdown H2 headings (##) with the exact section titles
- Do not add or remove sections (except optional merge block when relevant)
- Emphasize credibility, clarity, and trust
- Never add information that is not true
- Keep bios concise and scannable
- Use bracketed placeholders for unknown facts

## clients

label: Clients
description: Client portfolio, logos, and proof of impact page.
prompt:
You are a senior B2B web strategist and copywriter.

1. Read the keyword list attached to this prompt.
2. Review attached Source Material.
3. Build a full Client landing page based on the topic.
4. Ensure every keywords in the keyword list is in the output.
5. Mark all keywords in bold.
6. If any keywords are missing in the output, provide a list at the end.

Output format (Markdown) - use the exact headings and order below:

- Page title: "Clients"
- Section 1: "Headline / Intro"
- Section 2: "Client Logos (Filtered by Industry)"
- Section 3: "Featured Case Studies" (include "See all case studies" link)
- Section 4: "Client Testimonials"
- Section 5: "Client Videos"
- Section 6: "Full Client List Access"
- CTA block: "Contact via form or email"

Constraints:

- Follow the exact section order and labels above
- Use Markdown H2 headings (##) with the exact section titles
- Do not add or remove sections
- Never add information that is not true
- Trust-first tone with concrete outcomes
- Use bracketed placeholders for unknown facts

Writing and editing prompts

2026-02-01T20:30:21Z

Saxtonmd77: Created page with "# Landing Page Templates Format: - Each template starts with a "##" line using the template id. - label and description are required. - Everything after "prompt:" belongs to the prompt until the next "##". ## locations label: Locations description: Global offices and delivery centers page. prompt: You are a senior B2B web strategist and copywriter for Intellias. 1. Read the keyword list attached to this prompt. 2. Review attached Source Material. 3. Build a full Loc..."

# Landing Page Templates

Format:

- Each template starts with a "##" line using the template id.
- label and description are required.
- Everything after "prompt:" belongs to the prompt until the next "##".

## locations

label: Locations
description: Global offices and delivery centers page.
prompt:
You are a senior B2B web strategist and copywriter for Intellias.

1. Read the keyword list attached to this prompt.
2. Review attached Source Material.
3. Build a full Locations landing page based on the topic.
4. Ensure every keywords in the keyword list is in the output.
5. Mark all keywords in bold.
6. If any keywords are missing in the output, provide a list at the end.

Output format (Markdown) - use the exact headings and order below:

- Page title: "Locations"
- Section 1: "Headline / Intro" (global reach + unified delivery message)
- Section 2: "Global Scale Summary" (3-6 metrics with placeholders if unknown)
- Section 3: "Locations by Region" (group by region/country; include city, office type, contact placeholders)
- Section 4: "Main Contact" (single global contact block)
- Section 5: "Regional Links" (region-specific services/offerings)
- CTA block: "Contact via form or email" (include suggested button + email copy)

Constraints:

- Follow the exact section order and labels above
- Use Markdown H2 headings (##) with the exact section titles
- Do not add or remove sections
- Modern, credible, global tone
- Never add information that is not true
- Clear scannable sections and short paragraphs
- Use bracketed placeholders for unknown facts (example: [Number of engineers])

## services

label: Services
description: Service overview page with capabilities, proof, and outcomes.
prompt:
You are a senior B2B web strategist and copywriter. The user message is the topic and context for this page (service name, domain, audience).

1. Read the keyword list attached to this prompt.
2. Review attached Source Material.
3. Build a full Services landing page based on the topic.
4. Ensure every keywords in the keyword list is in the output.
5. Mark all keywords in bold.
6. If any keywords are missing in the output, provide a list at the end.

Output format (Markdown) - use the exact headings and order below:

- Page title: "Services"
- Section 1: "Hero — Headline & Value Proposition (Mandatory)" (keep this section short; include a note for a page progress bar)
- Section 2: "Client Logos (Mandatory)" (logos row immediately after hero)
- Section 3: "Problem Statement / Why It Matters / Challenges We Solve (Mandatory)"
- Section 4: "What We Offer — Services / Capabilities / Deliverables (Mandatory)"
- Section 5: "Client Success Stories / Case Studies / Social Proof / Partnerships (Mandatory)" (multiple compact examples)
- Section 6: "Our Approach / How We Deliver Value (Optional)" (stage-by-stage, outcome-focused)
- Section 7: "Benefits & Value Outcomes (Optional)" (impact metrics and results)
- Section 8: "Differentiators / Why Choose Us (Optional)"
- Section 9: "Use Cases & Industry/Domain Examples (Optional)" (tab system)
- Section 10: "Expert Snapshot (Optional)" (short bios only)
- Section 11: "FAQs (Mandatory)"
- Section 12: "Related Content & Interlinks (Mandatory)"
- CTA block: "Contact via form or email"

Constraints:

- Follow the exact section order and labels above
- Use Markdown H2 headings (##) with the exact section titles
- Do not add or remove sections
- Use concise, outcome-focused copy
- Never add information that is not true
- Use bracketed placeholders for unknown facts

## industries

label: Industrie
description: Industry overview or specialization page.
prompt:
You are a senior B2B web strategist and copywriter. Decide which level to use:

- If the topic is a broad industry (example: Retail, Mobility, Digital Health), use Level 1.
- If the topic is a sub-industry or specialization (example: Retail AI, Medical Devices, ADAS), use Level 2/3.

1. Read the keyword list attached to this prompt.
2. Review attached Source Material.
3. Build a full Industry landing page based on the topic.
4. Ensure every keywords in the keyword list is in the output.
5. Mark all keywords in bold.
6. If any keywords are missing in the output, provide a list at the end.

Output format (Markdown):

- Page title: "Industries"

If Level 1 (Industry Overview) use the exact headings and order below:

- Section 1: "Hero — Industry Value Proposition"
- Section 2: "Industry-Specific Capabilities Overview"
- Section 3: "Entry Points to Sub-Industry Pages"
- Section 4: "Representative Use Cases / Impact Examples"
- Section 5: "Social Proof + Client Logos"
- Section 6: "Curated Insights & Related Content"
- CTA block: "Contact via form or email"

If Level 2/3 (Specialization) use the exact headings and order below:

- Section 1: "Hero — Specialized Value Proposition"
- Section 2: "Specific Challenges / Problems Solved"
- Section 3: "Specialized Services & Capabilities"
- Section 4: "Detailed Approach — How We Deliver Value (Optional)"
- Section 5: "Use Cases (Tabbed)"
- Section 6: "Multiple Case Studies"
- Section 7: "Impact Numbers / Outcomes"
- Section 8: "Social Proof / Certifications / Partnerships"
- Section 9: "Related Pages & Parent Industry"
- CTA block: "Contact via form or email"

Constraints:

- Follow the exact section order and labels above for the chosen level
- Use Markdown H2 headings (##) with the exact section titles
- Do not add or remove sections
- Never add information that is not true
- Modern, industry-specific tone
- Use bracketed placeholders for unknown facts

## leadership

label: Leadership
description: Leadership team introduction and credibility page.
prompt:
You are a senior B2B web strategist and copywriter.

1. Read the keyword list attached to this prompt.
2. Review attached Source Material.
3. Build a full Leadership landing page based on the topic.
4. Ensure every keywords in the keyword list is in the output.
5. Mark all keywords in bold.
6. If any keywords are missing in the output, provide a list at the end.

Output format (Markdown) - use the exact headings and order below:

- Page title: "Leadership"
- Section 1: "Headline / Intro"
- Section 2: "Team Overview"
- Section 3: "Leadership Bios"
- Section 4: "Values & Vision"
- Optional Section: "Who We Are (Merge Option)"
- CTA block: "Contact via form or email"

Constraints:

- Follow the exact section order and labels above
- Use Markdown H2 headings (##) with the exact section titles
- Do not add or remove sections (except optional merge block when relevant)
- Emphasize credibility, clarity, and trust
- Never add information that is not true
- Keep bios concise and scannable
- Use bracketed placeholders for unknown facts

## clients

label: Clients
description: Client portfolio, logos, and proof of impact page.
prompt:
You are a senior B2B web strategist and copywriter.

1. Read the keyword list attached to this prompt.
2. Review attached Source Material.
3. Build a full Client landing page based on the topic.
4. Ensure every keywords in the keyword list is in the output.
5. Mark all keywords in bold.
6. If any keywords are missing in the output, provide a list at the end.

Output format (Markdown) - use the exact headings and order below:

- Page title: "Clients"
- Section 1: "Headline / Intro"
- Section 2: "Client Logos (Filtered by Industry)"
- Section 3: "Featured Case Studies" (include "See all case studies" link)
- Section 4: "Client Testimonials"
- Section 5: "Client Videos"
- Section 6: "Full Client List Access"
- CTA block: "Contact via form or email"

Constraints:

- Follow the exact section order and labels above
- Use Markdown H2 headings (##) with the exact section titles
- Do not add or remove sections
- Never add information that is not true
- Trust-first tone with concrete outcomes
- Use bracketed placeholders for unknown facts

Righting Sentences - User Guide

2026-01-28T00:33:44Z

Saxtonmd77: /* 4.2 Applying Settings */

=Righting Sentences User Guide=

Last updated: January 2026

Production URL: https://righting-sentences-573737403792.us-east1.run.app/

GitHub Project: https://github.com/saxtonmd/righting-sentences

Current version: 3.0.4

==Desktop user interface==
[[Image: Righting-Sentences-Desktop-Light.png|800px]]

==Mobile User Interface==
[[Image: Righting-Sentences-Mobile-Light.-3.0.4.png|300px]]

__TOC__

== 1. Purpose and Scope ==
'''Righting Sentences''' is a web-based chat application that generates better sentences from generative AI models. Prompts provide instructions to the models. The models then respond. Responses are expected to be more like standard written English. This means they should not contain repetitive triads, em dashes, or many words that genAI models frequently use. The goal is to make models that generate more human-like text.

How it works:

#Users prompt an OpenAI, Anthropic, or Google model
#A set of instructions encourages the model to return a response using its typical patterns
#The program captures the model's response
#*The first response is saved as a JSONL file in a Google bucket
#*The first response is scored as an example of '''Bad'''' model behavior
#A new prompt forces the models to generate a second response with editorial corrections
#*The second response is saved as a JSONL file in a Google bucket
#*The second response is scored as an example of '''Good'''' model behavior
#The program then forces changes if the models violate the restrictions
#The final output then appears
#The '''Good''' and '''Bad''' examples will fine-tune a foundational model

=== 1.1 Who this is for ===
----
*Writers
*Editors
*Journalists
*Marketers
*Researchers
*Assisstants
*Analysts
*Data enthusiasts
*Software developers

=== 1.2 Setting Realistic Expectations ===
----
This is a generative AI application. However, it is also a data science experiment. While Righting Sentences is like many public genAI apps, it is not the same.

* Expect occasional bugs in the user interface.
* Expect some responses to be slower to generate because of the two-prompt system.
* Expect periodic odd sentence constructions, and expect to edit the text.

The application is under continuous development.

=== 1.3 Warnings ===
----
Like other genAI apps, Righting Sentences can make mistakes. Furthermore, word pairings might be incorrect because the application determined that the correct method violated its instructions. While this behavior is by design, it should not be considered production-ready.

* Do not rely on Righting Sentences as a guaranteed source of truth. Generative AI can make mistakes.
* Do not use this software to replace advice from a doctor, lawyer, electrician, or other relevant professional.
* Do not use this software to generate content straight to production.

== 2. Getting Started ==

=== 2.1 Google Authentication ===
----
To use the application, you will need to sign in using the Google account associated with this project.

# Navigate to https://righting-sentences-573737403792.us-east1.run.app/
# Select '''Sign in with Google'''
# Enter the ''Username'' and ''Password'' for the Google account associated with this project
# Click '''Continue''' to accept the Terms of Service

You will be at the application's main screen.

== 3. Left Sidebar ==

The left sidebar contains:
* Your chat history
* The model selector
* A menu for app functions

To access each collapsed section:
* Hover the cursor over the ''Model'' selector to reveal the model selector and '''New Chat''' button
* Hover the cursor over the ''Menu'' to reveal '''Account''', '''Settings''', '''Help''', and '''Sign Out''' options

=== 3.0.1 Open and Close the Sidebar ===
* To close: select the '''X''' at the top right of the sidebar
* To open: select the hamburger menu (☰) at the top left

== 3.1 Chat History and Controls ==

=== 3.1.1 Chat history list ===
Each row in the chat history list shows:
* The conversation title
* The model used

To open a conversation:
# Navigate to the left sidebar
# Select the desired conversation

=== 3.1.2 Delete a conversation ===
To delete a conversation:
# Navigate to the chat history list
# Select the '''trash''' icon to the right of the conversation

Notes
* '''Deleting a conversation removes it from your chat history'''

== 4.2 Settings ==
====4.2.2 Color====
----
Righting Sentences offers nine theme colors. The default color is '''Blue'''. Other color selections are:
*Purple
*Pink
*Red
*Orange
*Yellow
*Green
*Teal
*Cyan

Selecting a new color changes the buttons, the user conversation bubble, and the outline of various page elements across the platform.

====4.2.2 Custom Instructions====
----
====4.2.3 Model Instructions====
----

== 4.3 Model Selector ==
The model selector controls which model is used for a new conversation.

=== 4.3.1 Select a model ===
# Navigate to the model selector in the left sidebar.
# Select the model you want.
# Select '''New Chat''' to start a conversation using that model.

=== 4.3.2 Important: models cannot be changed mid-chat ===
Once a conversation has messages, the model selector is disabled for that conversation.

To change models:
# Select '''New Chat'''.
# Select a different model.
# Continue in the new conversation.

=== 4.3.3 Available models ===
The model list can change over time. Typical configured models include:
{| class="wikitable"
! Provider !! Example model names !! Notes
|-
| OpenAI || gpt-4o; gpt-5.2-pro || Used for general writing assistance and editing.
|-
| Anthropic || claude-sonnet-4-5-20250929 || Used for alternative writing style and reasoning.
|-
| Google || gemini-3-flash-preview || Used for fast drafting and variations.
|}

== 4.3 Main Chat Window ==
The main chat window contains:
* The header (conversation title and model indicator).
* The message transcript.
* The message input box and file upload controls.

=== 4.3.1 Header ===
The header shows:
* The conversation title (center/left)
* The current model badge (top right)

=== 4.3.2 Messages ===
Messages appear as bubbles:
* Your messages are on the right.
* Assistant messages are on the left.

Assistant messages can include formatting such as:
* bullet lists
* headings
* code blocks

=== 4.3.3 Copy assistant output ===
Each assistant message includes a copy control:
# Navigate to the assistant message you want.
# Hover the message bubble.
# Select the copy control at the bottom-right of the bubble.

== 5. Writing and Editing Workflow ==
== 5.1 How to ask for what you want ==
GenAI performs best when you provide clear context and constraints.

Recommended prompt pattern:
* What you are writing (email, report, press release, article, résumé).
* Your audience (customer, internal team, general public).
* Desired tone (formal, neutral, friendly, direct).
* Length constraints (e.g., “under 150 words”).
* Required content (facts, names, dates).

Example:
<pre>
Rewrite the following paragraph for a general audience. Keep it under 120 words and use a neutral tone:
...
</pre>

== 5.2 What responses should look like ==
The assistant should typically return:
* A polished version of your text, and/or
* Clearly labeled alternatives (Option A, Option B), and/or
* A short explanation of major edits (when helpful).

If the assistant output is not what you want:
* Select a specific change (tone, length, structure).
* Ask for a second version rather than editing line-by-line.

== 5.3 Editorial behavior (two-pass system) ==
Righting Sentences uses an editorial process designed to reduce “AI-sounding” language.

What you may notice:
* Responses may be rewritten to sound more natural and human.
* Some words or phrasing patterns may be avoided by design.

== 6. File Uploads ==
You can upload files to a conversation so the assistant can reference them when responding.

=== 6.1 Upload a file ===
# Navigate to the message input area.
# Select '''Upload'''.
# Select one or more files.

After upload:
* Files appear as “chips” above the input box.
* If the file can be parsed, it may show a “Parsed” status.

=== 6.2 Remove an uploaded file ===
# Navigate to the file chip above the message box.
# Select the remove (×) control on the chip.
Removing a file deletes it from the conversation’s context, so the assistant will no longer reference it.

=== 6.3 Supported file types ===
The application is designed to accept:
* Text: .txt, .md, .csv, .tsv, .json
* Documents: .pdf, .doc, .docx
* Presentations: .ppt, .pptx
* Spreadsheets: .xls, .xlsx
* Images: .png, .jpg/.jpeg, .gif, .webp, .bmp, .tiff

Notes:
* Parsing quality varies by file type and content.
* Very large or image-heavy documents may be partially parsed.

=== 6.4 File size limits ===
The default maximum upload size is 25 MB per file (configurable by the administrator).

=== 6.5 How uploaded files are used by the model ===
If a file is successfully parsed, the extracted text is attached to the conversation context so the model can reference it when answering your questions.

Tip:
* Ask questions that cite the file: “In the uploaded document, what are the main recommendations?”
* If the assistant says it cannot see the file, re-upload a text-friendly version or paste key sections into the chat.

== 7. Settings ==
Navigate to '''Settings''' from the left sidebar menu.

=== 7.1 Theme ===
Select a theme:
* '''Light'''
* '''Dark'''
* '''System''' (matches your OS preference)

=== 7.2 Primary color ===
Select a primary color to change accent styling (borders, icons, buttons).

=== 7.3 Custom instructions ===
Use '''Custom Instructions''' to provide information about your preferences (tone, style, constraints).

=== 7.4 LLM instructions ===
Use '''LLM Instructions''' to specify global rules for how the assistant should respond.

== 8. Account ==
Navigate to '''Account''' from the left sidebar menu.

The account page shows:
* Your Google profile photo (when available)
* Your name and email
* A '''Sign Out''' button

== 9. Data Storage, Privacy, and Access ==
=== 9.1 What is stored ===
The system stores:
* Conversations and messages (including your prompts and assistant responses)
* Uploaded files and file metadata
* Optional research logs for the editorial system (when enabled)

Because this is a data science project, assume that your prompts, responses, and uploaded content may be reviewed by the project administrator for research and quality improvement.

=== 9.2 Where data is stored ===
Data is stored in Google Cloud services:
* Conversation metadata and message content are stored in Google Cloud Firestore.
* Uploaded file objects are stored in Google Cloud Storage in a private bucket in the project’s Google Cloud environment.

=== 9.3 Who can access data ===
Data access is restricted to:
* The project owner and administrators for the underlying Google Cloud project (Saxton Publishing).

=== 9.4 Third-party model providers ===
When you send a message, the conversation content may be transmitted to the selected model provider to generate a response.

When you upload a file:
* Text may be extracted locally for common formats.
* In some cases (especially images), file content may be sent to a model provider for extraction (OCR/parsing) depending on configuration.

== 10. Troubleshooting ==
=== 10.1 I cannot sign in ===
* Confirm you are using a Google account.
* Confirm your account has been invited.
* If the problem persists, contact Saxton Publishing.

=== 10.2 I cannot change the model ===
This is expected once a conversation has messages.

To change models:
# Select '''New Chat'''.
# Select a different model.

=== 10.3 My file upload fails ===
If you see an upload error:
* The storage bucket may not be configured or may not exist.
* The server may not have permission to write to storage.

Contact the administrator with the exact error message.

=== 10.4 The assistant says it cannot access my file ===
* Confirm the file chip is visible above the message box.
* Upload a smaller version of the file, or a text-based export (for example, export a Word doc to .txt).
* For scanned PDFs or images, upload a clearer image or provide the text in the chat.

Righting Sentences - User Guide

2026-01-28T00:32:57Z

Saxtonmd77: /* 3.1.2 Delete a conversation */

=Righting Sentences User Guide=

Last updated: January 2026

Production URL: https://righting-sentences-573737403792.us-east1.run.app/

GitHub Project: https://github.com/saxtonmd/righting-sentences

Current version: 3.0.4

==Desktop user interface==
[[Image: Righting-Sentences-Desktop-Light.png|800px]]

==Mobile User Interface==
[[Image: Righting-Sentences-Mobile-Light.-3.0.4.png|300px]]

__TOC__

== 1. Purpose and Scope ==
'''Righting Sentences''' is a web-based chat application that generates better sentences from generative AI models. Prompts provide instructions to the models. The models then respond. Responses are expected to be more like standard written English. This means they should not contain repetitive triads, em dashes, or many words that genAI models frequently use. The goal is to make models that generate more human-like text.

How it works:

#Users prompt an OpenAI, Anthropic, or Google model
#A set of instructions encourages the model to return a response using its typical patterns
#The program captures the model's response
#*The first response is saved as a JSONL file in a Google bucket
#*The first response is scored as an example of '''Bad'''' model behavior
#A new prompt forces the models to generate a second response with editorial corrections
#*The second response is saved as a JSONL file in a Google bucket
#*The second response is scored as an example of '''Good'''' model behavior
#The program then forces changes if the models violate the restrictions
#The final output then appears
#The '''Good''' and '''Bad''' examples will fine-tune a foundational model

=== 1.1 Who this is for ===
----
*Writers
*Editors
*Journalists
*Marketers
*Researchers
*Assisstants
*Analysts
*Data enthusiasts
*Software developers

=== 1.2 Setting Realistic Expectations ===
----
This is a generative AI application. However, it is also a data science experiment. While Righting Sentences is like many public genAI apps, it is not the same.

* Expect occasional bugs in the user interface.
* Expect some responses to be slower to generate because of the two-prompt system.
* Expect periodic odd sentence constructions, and expect to edit the text.

The application is under continuous development.

=== 1.3 Warnings ===
----
Like other genAI apps, Righting Sentences can make mistakes. Furthermore, word pairings might be incorrect because the application determined that the correct method violated its instructions. While this behavior is by design, it should not be considered production-ready.

* Do not rely on Righting Sentences as a guaranteed source of truth. Generative AI can make mistakes.
* Do not use this software to replace advice from a doctor, lawyer, electrician, or other relevant professional.
* Do not use this software to generate content straight to production.

== 2. Getting Started ==

=== 2.1 Google Authentication ===
----
To use the application, you will need to sign in using the Google account associated with this project.

# Navigate to https://righting-sentences-573737403792.us-east1.run.app/
# Select '''Sign in with Google'''
# Enter the ''Username'' and ''Password'' for the Google account associated with this project
# Click '''Continue''' to accept the Terms of Service

You will be at the application's main screen.

== 3. Left Sidebar ==

The left sidebar contains:
* Your chat history
* The model selector
* A menu for app functions

To access each collapsed section:
* Hover the cursor over the ''Model'' selector to reveal the model selector and '''New Chat''' button
* Hover the cursor over the ''Menu'' to reveal '''Account''', '''Settings''', '''Help''', and '''Sign Out''' options

=== 3.0.1 Open and Close the Sidebar ===
* To close: select the '''X''' at the top right of the sidebar
* To open: select the hamburger menu (☰) at the top left

== 3.1 Chat History and Controls ==

=== 3.1.1 Chat history list ===
Each row in the chat history list shows:
* The conversation title
* The model used

To open a conversation:
# Navigate to the left sidebar
# Select the desired conversation

=== 3.1.2 Delete a conversation ===
To delete a conversation:
# Navigate to the chat history list
# Select the '''trash''' icon to the right of the conversation

Notes
* '''Deleting a conversation removes it from your chat history'''

== 4.2 Applying Settings ==
====4.2.2 Color====
----
Righting Sentences offers nine theme colors. The default color is '''Blue'''. Other color selections are:
*Purple
*Pink
*Red
*Orange
*Yellow
*Green
*Teal
*Cyan

Selecting a new color changes the buttons, the user conversation bubble, and the outline of various page elements across the platform.

====4.2.2 Custom Instructions====
----
====4.2.3 Model Instructions====
----

== 4.3 Model Selector ==
The model selector controls which model is used for a new conversation.

=== 4.3.1 Select a model ===
# Navigate to the model selector in the left sidebar.
# Select the model you want.
# Select '''New Chat''' to start a conversation using that model.

=== 4.3.2 Important: models cannot be changed mid-chat ===
Once a conversation has messages, the model selector is disabled for that conversation.

To change models:
# Select '''New Chat'''.
# Select a different model.
# Continue in the new conversation.

=== 4.3.3 Available models ===
The model list can change over time. Typical configured models include:
{| class="wikitable"
! Provider !! Example model names !! Notes
|-
| OpenAI || gpt-4o; gpt-5.2-pro || Used for general writing assistance and editing.
|-
| Anthropic || claude-sonnet-4-5-20250929 || Used for alternative writing style and reasoning.
|-
| Google || gemini-3-flash-preview || Used for fast drafting and variations.
|}

== 4.3 Main Chat Window ==
The main chat window contains:
* The header (conversation title and model indicator).
* The message transcript.
* The message input box and file upload controls.

=== 4.3.1 Header ===
The header shows:
* The conversation title (center/left)
* The current model badge (top right)

=== 4.3.2 Messages ===
Messages appear as bubbles:
* Your messages are on the right.
* Assistant messages are on the left.

Assistant messages can include formatting such as:
* bullet lists
* headings
* code blocks

=== 4.3.3 Copy assistant output ===
Each assistant message includes a copy control:
# Navigate to the assistant message you want.
# Hover the message bubble.
# Select the copy control at the bottom-right of the bubble.

== 5. Writing and Editing Workflow ==
== 5.1 How to ask for what you want ==
GenAI performs best when you provide clear context and constraints.

Recommended prompt pattern:
* What you are writing (email, report, press release, article, résumé).
* Your audience (customer, internal team, general public).
* Desired tone (formal, neutral, friendly, direct).
* Length constraints (e.g., “under 150 words”).
* Required content (facts, names, dates).

Example:
<pre>
Rewrite the following paragraph for a general audience. Keep it under 120 words and use a neutral tone:
...
</pre>

== 5.2 What responses should look like ==
The assistant should typically return:
* A polished version of your text, and/or
* Clearly labeled alternatives (Option A, Option B), and/or
* A short explanation of major edits (when helpful).

If the assistant output is not what you want:
* Select a specific change (tone, length, structure).
* Ask for a second version rather than editing line-by-line.

== 5.3 Editorial behavior (two-pass system) ==
Righting Sentences uses an editorial process designed to reduce “AI-sounding” language.

What you may notice:
* Responses may be rewritten to sound more natural and human.
* Some words or phrasing patterns may be avoided by design.

== 6. File Uploads ==
You can upload files to a conversation so the assistant can reference them when responding.

=== 6.1 Upload a file ===
# Navigate to the message input area.
# Select '''Upload'''.
# Select one or more files.

After upload:
* Files appear as “chips” above the input box.
* If the file can be parsed, it may show a “Parsed” status.

=== 6.2 Remove an uploaded file ===
# Navigate to the file chip above the message box.
# Select the remove (×) control on the chip.
Removing a file deletes it from the conversation’s context, so the assistant will no longer reference it.

=== 6.3 Supported file types ===
The application is designed to accept:
* Text: .txt, .md, .csv, .tsv, .json
* Documents: .pdf, .doc, .docx
* Presentations: .ppt, .pptx
* Spreadsheets: .xls, .xlsx
* Images: .png, .jpg/.jpeg, .gif, .webp, .bmp, .tiff

Notes:
* Parsing quality varies by file type and content.
* Very large or image-heavy documents may be partially parsed.

=== 6.4 File size limits ===
The default maximum upload size is 25 MB per file (configurable by the administrator).

=== 6.5 How uploaded files are used by the model ===
If a file is successfully parsed, the extracted text is attached to the conversation context so the model can reference it when answering your questions.

Tip:
* Ask questions that cite the file: “In the uploaded document, what are the main recommendations?”
* If the assistant says it cannot see the file, re-upload a text-friendly version or paste key sections into the chat.

== 7. Settings ==
Navigate to '''Settings''' from the left sidebar menu.

=== 7.1 Theme ===
Select a theme:
* '''Light'''
* '''Dark'''
* '''System''' (matches your OS preference)

=== 7.2 Primary color ===
Select a primary color to change accent styling (borders, icons, buttons).

=== 7.3 Custom instructions ===
Use '''Custom Instructions''' to provide information about your preferences (tone, style, constraints).

=== 7.4 LLM instructions ===
Use '''LLM Instructions''' to specify global rules for how the assistant should respond.

== 8. Account ==
Navigate to '''Account''' from the left sidebar menu.

The account page shows:
* Your Google profile photo (when available)
* Your name and email
* A '''Sign Out''' button

== 9. Data Storage, Privacy, and Access ==
=== 9.1 What is stored ===
The system stores:
* Conversations and messages (including your prompts and assistant responses)
* Uploaded files and file metadata
* Optional research logs for the editorial system (when enabled)

Because this is a data science project, assume that your prompts, responses, and uploaded content may be reviewed by the project administrator for research and quality improvement.

=== 9.2 Where data is stored ===
Data is stored in Google Cloud services:
* Conversation metadata and message content are stored in Google Cloud Firestore.
* Uploaded file objects are stored in Google Cloud Storage in a private bucket in the project’s Google Cloud environment.

=== 9.3 Who can access data ===
Data access is restricted to:
* The project owner and administrators for the underlying Google Cloud project (Saxton Publishing).

=== 9.4 Third-party model providers ===
When you send a message, the conversation content may be transmitted to the selected model provider to generate a response.

When you upload a file:
* Text may be extracted locally for common formats.
* In some cases (especially images), file content may be sent to a model provider for extraction (OCR/parsing) depending on configuration.

== 10. Troubleshooting ==
=== 10.1 I cannot sign in ===
* Confirm you are using a Google account.
* Confirm your account has been invited.
* If the problem persists, contact Saxton Publishing.

=== 10.2 I cannot change the model ===
This is expected once a conversation has messages.

To change models:
# Select '''New Chat'''.
# Select a different model.

=== 10.3 My file upload fails ===
If you see an upload error:
* The storage bucket may not be configured or may not exist.
* The server may not have permission to write to storage.

Contact the administrator with the exact error message.

=== 10.4 The assistant says it cannot access my file ===
* Confirm the file chip is visible above the message box.
* Upload a smaller version of the file, or a text-based export (for example, export a Word doc to .txt).
* For scanned PDFs or images, upload a clearer image or provide the text in the chat.

Righting Sentences - User Guide

2026-01-28T00:32:35Z

Saxtonmd77: /* 3.1.2 Delete a conversation */

=Righting Sentences User Guide=

Last updated: January 2026

Production URL: https://righting-sentences-573737403792.us-east1.run.app/

GitHub Project: https://github.com/saxtonmd/righting-sentences

Current version: 3.0.4

==Desktop user interface==
[[Image: Righting-Sentences-Desktop-Light.png|800px]]

==Mobile User Interface==
[[Image: Righting-Sentences-Mobile-Light.-3.0.4.png|300px]]

__TOC__

== 1. Purpose and Scope ==
'''Righting Sentences''' is a web-based chat application that generates better sentences from generative AI models. Prompts provide instructions to the models. The models then respond. Responses are expected to be more like standard written English. This means they should not contain repetitive triads, em dashes, or many words that genAI models frequently use. The goal is to make models that generate more human-like text.

How it works:

#Users prompt an OpenAI, Anthropic, or Google model
#A set of instructions encourages the model to return a response using its typical patterns
#The program captures the model's response
#*The first response is saved as a JSONL file in a Google bucket
#*The first response is scored as an example of '''Bad'''' model behavior
#A new prompt forces the models to generate a second response with editorial corrections
#*The second response is saved as a JSONL file in a Google bucket
#*The second response is scored as an example of '''Good'''' model behavior
#The program then forces changes if the models violate the restrictions
#The final output then appears
#The '''Good''' and '''Bad''' examples will fine-tune a foundational model

=== 1.1 Who this is for ===
----
*Writers
*Editors
*Journalists
*Marketers
*Researchers
*Assisstants
*Analysts
*Data enthusiasts
*Software developers

=== 1.2 Setting Realistic Expectations ===
----
This is a generative AI application. However, it is also a data science experiment. While Righting Sentences is like many public genAI apps, it is not the same.

* Expect occasional bugs in the user interface.
* Expect some responses to be slower to generate because of the two-prompt system.
* Expect periodic odd sentence constructions, and expect to edit the text.

The application is under continuous development.

=== 1.3 Warnings ===
----
Like other genAI apps, Righting Sentences can make mistakes. Furthermore, word pairings might be incorrect because the application determined that the correct method violated its instructions. While this behavior is by design, it should not be considered production-ready.

* Do not rely on Righting Sentences as a guaranteed source of truth. Generative AI can make mistakes.
* Do not use this software to replace advice from a doctor, lawyer, electrician, or other relevant professional.
* Do not use this software to generate content straight to production.

== 2. Getting Started ==

=== 2.1 Google Authentication ===
----
To use the application, you will need to sign in using the Google account associated with this project.

# Navigate to https://righting-sentences-573737403792.us-east1.run.app/
# Select '''Sign in with Google'''
# Enter the ''Username'' and ''Password'' for the Google account associated with this project
# Click '''Continue''' to accept the Terms of Service

You will be at the application's main screen.

== 3. Left Sidebar ==

The left sidebar contains:
* Your chat history
* The model selector
* A menu for app functions

To access each collapsed section:
* Hover the cursor over the ''Model'' selector to reveal the model selector and '''New Chat''' button
* Hover the cursor over the ''Menu'' to reveal '''Account''', '''Settings''', '''Help''', and '''Sign Out''' options

=== 3.0.1 Open and Close the Sidebar ===
* To close: select the '''X''' at the top right of the sidebar
* To open: select the hamburger menu (☰) at the top left

== 3.1 Chat History and Controls ==

=== 3.1.1 Chat history list ===
Each row in the chat history list shows:
* The conversation title
* The model used

To open a conversation:
# Navigate to the left sidebar
# Select the desired conversation

=== 3.1.2 Delete a conversation ===
To delete a conversation:
# Navigate to the chat history list
# Select the ''''trash'''' icon to the right of the conversation

Notes
* ''''Deleting a conversation removes it from your chat history''''

== 4.2 Applying Settings ==
====4.2.2 Color====
----
Righting Sentences offers nine theme colors. The default color is '''Blue'''. Other color selections are:
*Purple
*Pink
*Red
*Orange
*Yellow
*Green
*Teal
*Cyan

Selecting a new color changes the buttons, the user conversation bubble, and the outline of various page elements across the platform.

====4.2.2 Custom Instructions====
----
====4.2.3 Model Instructions====
----

== 4.3 Model Selector ==
The model selector controls which model is used for a new conversation.

=== 4.3.1 Select a model ===
# Navigate to the model selector in the left sidebar.
# Select the model you want.
# Select '''New Chat''' to start a conversation using that model.

=== 4.3.2 Important: models cannot be changed mid-chat ===
Once a conversation has messages, the model selector is disabled for that conversation.

To change models:
# Select '''New Chat'''.
# Select a different model.
# Continue in the new conversation.

=== 4.3.3 Available models ===
The model list can change over time. Typical configured models include:
{| class="wikitable"
! Provider !! Example model names !! Notes
|-
| OpenAI || gpt-4o; gpt-5.2-pro || Used for general writing assistance and editing.
|-
| Anthropic || claude-sonnet-4-5-20250929 || Used for alternative writing style and reasoning.
|-
| Google || gemini-3-flash-preview || Used for fast drafting and variations.
|}

== 4.3 Main Chat Window ==
The main chat window contains:
* The header (conversation title and model indicator).
* The message transcript.
* The message input box and file upload controls.

=== 4.3.1 Header ===
The header shows:
* The conversation title (center/left)
* The current model badge (top right)

=== 4.3.2 Messages ===
Messages appear as bubbles:
* Your messages are on the right.
* Assistant messages are on the left.

Assistant messages can include formatting such as:
* bullet lists
* headings
* code blocks

=== 4.3.3 Copy assistant output ===
Each assistant message includes a copy control:
# Navigate to the assistant message you want.
# Hover the message bubble.
# Select the copy control at the bottom-right of the bubble.

== 5. Writing and Editing Workflow ==
== 5.1 How to ask for what you want ==
GenAI performs best when you provide clear context and constraints.

Recommended prompt pattern:
* What you are writing (email, report, press release, article, résumé).
* Your audience (customer, internal team, general public).
* Desired tone (formal, neutral, friendly, direct).
* Length constraints (e.g., “under 150 words”).
* Required content (facts, names, dates).

Example:
<pre>
Rewrite the following paragraph for a general audience. Keep it under 120 words and use a neutral tone:
...
</pre>

== 5.2 What responses should look like ==
The assistant should typically return:
* A polished version of your text, and/or
* Clearly labeled alternatives (Option A, Option B), and/or
* A short explanation of major edits (when helpful).

If the assistant output is not what you want:
* Select a specific change (tone, length, structure).
* Ask for a second version rather than editing line-by-line.

== 5.3 Editorial behavior (two-pass system) ==
Righting Sentences uses an editorial process designed to reduce “AI-sounding” language.

What you may notice:
* Responses may be rewritten to sound more natural and human.
* Some words or phrasing patterns may be avoided by design.

== 6. File Uploads ==
You can upload files to a conversation so the assistant can reference them when responding.

=== 6.1 Upload a file ===
# Navigate to the message input area.
# Select '''Upload'''.
# Select one or more files.

After upload:
* Files appear as “chips” above the input box.
* If the file can be parsed, it may show a “Parsed” status.

=== 6.2 Remove an uploaded file ===
# Navigate to the file chip above the message box.
# Select the remove (×) control on the chip.
Removing a file deletes it from the conversation’s context, so the assistant will no longer reference it.

=== 6.3 Supported file types ===
The application is designed to accept:
* Text: .txt, .md, .csv, .tsv, .json
* Documents: .pdf, .doc, .docx
* Presentations: .ppt, .pptx
* Spreadsheets: .xls, .xlsx
* Images: .png, .jpg/.jpeg, .gif, .webp, .bmp, .tiff

Notes:
* Parsing quality varies by file type and content.
* Very large or image-heavy documents may be partially parsed.

=== 6.4 File size limits ===
The default maximum upload size is 25 MB per file (configurable by the administrator).

=== 6.5 How uploaded files are used by the model ===
If a file is successfully parsed, the extracted text is attached to the conversation context so the model can reference it when answering your questions.

Tip:
* Ask questions that cite the file: “In the uploaded document, what are the main recommendations?”
* If the assistant says it cannot see the file, re-upload a text-friendly version or paste key sections into the chat.

== 7. Settings ==
Navigate to '''Settings''' from the left sidebar menu.

=== 7.1 Theme ===
Select a theme:
* '''Light'''
* '''Dark'''
* '''System''' (matches your OS preference)

=== 7.2 Primary color ===
Select a primary color to change accent styling (borders, icons, buttons).

=== 7.3 Custom instructions ===
Use '''Custom Instructions''' to provide information about your preferences (tone, style, constraints).

=== 7.4 LLM instructions ===
Use '''LLM Instructions''' to specify global rules for how the assistant should respond.

== 8. Account ==
Navigate to '''Account''' from the left sidebar menu.

The account page shows:
* Your Google profile photo (when available)
* Your name and email
* A '''Sign Out''' button

== 9. Data Storage, Privacy, and Access ==
=== 9.1 What is stored ===
The system stores:
* Conversations and messages (including your prompts and assistant responses)
* Uploaded files and file metadata
* Optional research logs for the editorial system (when enabled)

Because this is a data science project, assume that your prompts, responses, and uploaded content may be reviewed by the project administrator for research and quality improvement.

=== 9.2 Where data is stored ===
Data is stored in Google Cloud services:
* Conversation metadata and message content are stored in Google Cloud Firestore.
* Uploaded file objects are stored in Google Cloud Storage in a private bucket in the project’s Google Cloud environment.

=== 9.3 Who can access data ===
Data access is restricted to:
* The project owner and administrators for the underlying Google Cloud project (Saxton Publishing).

=== 9.4 Third-party model providers ===
When you send a message, the conversation content may be transmitted to the selected model provider to generate a response.

When you upload a file:
* Text may be extracted locally for common formats.
* In some cases (especially images), file content may be sent to a model provider for extraction (OCR/parsing) depending on configuration.

== 10. Troubleshooting ==
=== 10.1 I cannot sign in ===
* Confirm you are using a Google account.
* Confirm your account has been invited.
* If the problem persists, contact Saxton Publishing.

=== 10.2 I cannot change the model ===
This is expected once a conversation has messages.

To change models:
# Select '''New Chat'''.
# Select a different model.

=== 10.3 My file upload fails ===
If you see an upload error:
* The storage bucket may not be configured or may not exist.
* The server may not have permission to write to storage.

Contact the administrator with the exact error message.

=== 10.4 The assistant says it cannot access my file ===
* Confirm the file chip is visible above the message box.
* Upload a smaller version of the file, or a text-based export (for example, export a Word doc to .txt).
* For scanned PDFs or images, upload a clearer image or provide the text in the chat.

Righting Sentences - User Guide

2026-01-28T00:31:56Z

Saxtonmd77: /* 3.1.2 Delete a conversation */

=Righting Sentences User Guide=

Last updated: January 2026

Production URL: https://righting-sentences-573737403792.us-east1.run.app/

GitHub Project: https://github.com/saxtonmd/righting-sentences

Current version: 3.0.4

==Desktop user interface==
[[Image: Righting-Sentences-Desktop-Light.png|800px]]

==Mobile User Interface==
[[Image: Righting-Sentences-Mobile-Light.-3.0.4.png|300px]]

__TOC__

== 1. Purpose and Scope ==
'''Righting Sentences''' is a web-based chat application that generates better sentences from generative AI models. Prompts provide instructions to the models. The models then respond. Responses are expected to be more like standard written English. This means they should not contain repetitive triads, em dashes, or many words that genAI models frequently use. The goal is to make models that generate more human-like text.

How it works:

#Users prompt an OpenAI, Anthropic, or Google model
#A set of instructions encourages the model to return a response using its typical patterns
#The program captures the model's response
#*The first response is saved as a JSONL file in a Google bucket
#*The first response is scored as an example of '''Bad'''' model behavior
#A new prompt forces the models to generate a second response with editorial corrections
#*The second response is saved as a JSONL file in a Google bucket
#*The second response is scored as an example of '''Good'''' model behavior
#The program then forces changes if the models violate the restrictions
#The final output then appears
#The '''Good''' and '''Bad''' examples will fine-tune a foundational model

=== 1.1 Who this is for ===
----
*Writers
*Editors
*Journalists
*Marketers
*Researchers
*Assisstants
*Analysts
*Data enthusiasts
*Software developers

=== 1.2 Setting Realistic Expectations ===
----
This is a generative AI application. However, it is also a data science experiment. While Righting Sentences is like many public genAI apps, it is not the same.

* Expect occasional bugs in the user interface.
* Expect some responses to be slower to generate because of the two-prompt system.
* Expect periodic odd sentence constructions, and expect to edit the text.

The application is under continuous development.

=== 1.3 Warnings ===
----
Like other genAI apps, Righting Sentences can make mistakes. Furthermore, word pairings might be incorrect because the application determined that the correct method violated its instructions. While this behavior is by design, it should not be considered production-ready.

* Do not rely on Righting Sentences as a guaranteed source of truth. Generative AI can make mistakes.
* Do not use this software to replace advice from a doctor, lawyer, electrician, or other relevant professional.
* Do not use this software to generate content straight to production.

== 2. Getting Started ==

=== 2.1 Google Authentication ===
----
To use the application, you will need to sign in using the Google account associated with this project.

# Navigate to https://righting-sentences-573737403792.us-east1.run.app/
# Select '''Sign in with Google'''
# Enter the ''Username'' and ''Password'' for the Google account associated with this project
# Click '''Continue''' to accept the Terms of Service

You will be at the application's main screen.

== 3. Left Sidebar ==

The left sidebar contains:
* Your chat history
* The model selector
* A menu for app functions

To access each collapsed section:
* Hover the cursor over the ''Model'' selector to reveal the model selector and '''New Chat''' button
* Hover the cursor over the ''Menu'' to reveal '''Account''', '''Settings''', '''Help''', and '''Sign Out''' options

=== 3.0.1 Open and Close the Sidebar ===
* To close: select the '''X''' at the top right of the sidebar
* To open: select the hamburger menu (☰) at the top left

== 3.1 Chat History and Controls ==

=== 3.1.1 Chat history list ===
Each row in the chat history list shows:
* The conversation title
* The model used

To open a conversation:
# Navigate to the left sidebar
# Select the desired conversation

=== 3.1.2 Delete a conversation ===
To delete a conversation:
# Navigate to the chat history list
# Select the trash icon to the right of the conversation

Notes
* ''''Deleting a conversation removes it from your chat history''''

== 4.2 Applying Settings ==
====4.2.2 Color====
----
Righting Sentences offers nine theme colors. The default color is '''Blue'''. Other color selections are:
*Purple
*Pink
*Red
*Orange
*Yellow
*Green
*Teal
*Cyan

Selecting a new color changes the buttons, the user conversation bubble, and the outline of various page elements across the platform.

====4.2.2 Custom Instructions====
----
====4.2.3 Model Instructions====
----

== 4.3 Model Selector ==
The model selector controls which model is used for a new conversation.

=== 4.3.1 Select a model ===
# Navigate to the model selector in the left sidebar.
# Select the model you want.
# Select '''New Chat''' to start a conversation using that model.

=== 4.3.2 Important: models cannot be changed mid-chat ===
Once a conversation has messages, the model selector is disabled for that conversation.

To change models:
# Select '''New Chat'''.
# Select a different model.
# Continue in the new conversation.

=== 4.3.3 Available models ===
The model list can change over time. Typical configured models include:
{| class="wikitable"
! Provider !! Example model names !! Notes
|-
| OpenAI || gpt-4o; gpt-5.2-pro || Used for general writing assistance and editing.
|-
| Anthropic || claude-sonnet-4-5-20250929 || Used for alternative writing style and reasoning.
|-
| Google || gemini-3-flash-preview || Used for fast drafting and variations.
|}

== 4.3 Main Chat Window ==
The main chat window contains:
* The header (conversation title and model indicator).
* The message transcript.
* The message input box and file upload controls.

=== 4.3.1 Header ===
The header shows:
* The conversation title (center/left)
* The current model badge (top right)

=== 4.3.2 Messages ===
Messages appear as bubbles:
* Your messages are on the right.
* Assistant messages are on the left.

Assistant messages can include formatting such as:
* bullet lists
* headings
* code blocks

=== 4.3.3 Copy assistant output ===
Each assistant message includes a copy control:
# Navigate to the assistant message you want.
# Hover the message bubble.
# Select the copy control at the bottom-right of the bubble.

== 5. Writing and Editing Workflow ==
== 5.1 How to ask for what you want ==
GenAI performs best when you provide clear context and constraints.

Recommended prompt pattern:
* What you are writing (email, report, press release, article, résumé).
* Your audience (customer, internal team, general public).
* Desired tone (formal, neutral, friendly, direct).
* Length constraints (e.g., “under 150 words”).
* Required content (facts, names, dates).

Example:
<pre>
Rewrite the following paragraph for a general audience. Keep it under 120 words and use a neutral tone:
...
</pre>

== 5.2 What responses should look like ==
The assistant should typically return:
* A polished version of your text, and/or
* Clearly labeled alternatives (Option A, Option B), and/or
* A short explanation of major edits (when helpful).

If the assistant output is not what you want:
* Select a specific change (tone, length, structure).
* Ask for a second version rather than editing line-by-line.

== 5.3 Editorial behavior (two-pass system) ==
Righting Sentences uses an editorial process designed to reduce “AI-sounding” language.

What you may notice:
* Responses may be rewritten to sound more natural and human.
* Some words or phrasing patterns may be avoided by design.

== 6. File Uploads ==
You can upload files to a conversation so the assistant can reference them when responding.

=== 6.1 Upload a file ===
# Navigate to the message input area.
# Select '''Upload'''.
# Select one or more files.

After upload:
* Files appear as “chips” above the input box.
* If the file can be parsed, it may show a “Parsed” status.

=== 6.2 Remove an uploaded file ===
# Navigate to the file chip above the message box.
# Select the remove (×) control on the chip.
Removing a file deletes it from the conversation’s context, so the assistant will no longer reference it.

=== 6.3 Supported file types ===
The application is designed to accept:
* Text: .txt, .md, .csv, .tsv, .json
* Documents: .pdf, .doc, .docx
* Presentations: .ppt, .pptx
* Spreadsheets: .xls, .xlsx
* Images: .png, .jpg/.jpeg, .gif, .webp, .bmp, .tiff

Notes:
* Parsing quality varies by file type and content.
* Very large or image-heavy documents may be partially parsed.

=== 6.4 File size limits ===
The default maximum upload size is 25 MB per file (configurable by the administrator).

=== 6.5 How uploaded files are used by the model ===
If a file is successfully parsed, the extracted text is attached to the conversation context so the model can reference it when answering your questions.

Tip:
* Ask questions that cite the file: “In the uploaded document, what are the main recommendations?”
* If the assistant says it cannot see the file, re-upload a text-friendly version or paste key sections into the chat.

== 7. Settings ==
Navigate to '''Settings''' from the left sidebar menu.

=== 7.1 Theme ===
Select a theme:
* '''Light'''
* '''Dark'''
* '''System''' (matches your OS preference)

=== 7.2 Primary color ===
Select a primary color to change accent styling (borders, icons, buttons).

=== 7.3 Custom instructions ===
Use '''Custom Instructions''' to provide information about your preferences (tone, style, constraints).

=== 7.4 LLM instructions ===
Use '''LLM Instructions''' to specify global rules for how the assistant should respond.

== 8. Account ==
Navigate to '''Account''' from the left sidebar menu.

The account page shows:
* Your Google profile photo (when available)
* Your name and email
* A '''Sign Out''' button

== 9. Data Storage, Privacy, and Access ==
=== 9.1 What is stored ===
The system stores:
* Conversations and messages (including your prompts and assistant responses)
* Uploaded files and file metadata
* Optional research logs for the editorial system (when enabled)

Because this is a data science project, assume that your prompts, responses, and uploaded content may be reviewed by the project administrator for research and quality improvement.

=== 9.2 Where data is stored ===
Data is stored in Google Cloud services:
* Conversation metadata and message content are stored in Google Cloud Firestore.
* Uploaded file objects are stored in Google Cloud Storage in a private bucket in the project’s Google Cloud environment.

=== 9.3 Who can access data ===
Data access is restricted to:
* The project owner and administrators for the underlying Google Cloud project (Saxton Publishing).

=== 9.4 Third-party model providers ===
When you send a message, the conversation content may be transmitted to the selected model provider to generate a response.

When you upload a file:
* Text may be extracted locally for common formats.
* In some cases (especially images), file content may be sent to a model provider for extraction (OCR/parsing) depending on configuration.

== 10. Troubleshooting ==
=== 10.1 I cannot sign in ===
* Confirm you are using a Google account.
* Confirm your account has been invited.
* If the problem persists, contact Saxton Publishing.

=== 10.2 I cannot change the model ===
This is expected once a conversation has messages.

To change models:
# Select '''New Chat'''.
# Select a different model.

=== 10.3 My file upload fails ===
If you see an upload error:
* The storage bucket may not be configured or may not exist.
* The server may not have permission to write to storage.

Contact the administrator with the exact error message.

=== 10.4 The assistant says it cannot access my file ===
* Confirm the file chip is visible above the message box.
* Upload a smaller version of the file, or a text-based export (for example, export a Word doc to .txt).
* For scanned PDFs or images, upload a clearer image or provide the text in the chat.

Righting Sentences - User Guide

2026-01-28T00:30:31Z

Saxtonmd77: /* 3.1.1 Chat history list */

=Righting Sentences User Guide=

Last updated: January 2026

Production URL: https://righting-sentences-573737403792.us-east1.run.app/

GitHub Project: https://github.com/saxtonmd/righting-sentences

Current version: 3.0.4

==Desktop user interface==
[[Image: Righting-Sentences-Desktop-Light.png|800px]]

==Mobile User Interface==
[[Image: Righting-Sentences-Mobile-Light.-3.0.4.png|300px]]

__TOC__

== 1. Purpose and Scope ==
'''Righting Sentences''' is a web-based chat application that generates better sentences from generative AI models. Prompts provide instructions to the models. The models then respond. Responses are expected to be more like standard written English. This means they should not contain repetitive triads, em dashes, or many words that genAI models frequently use. The goal is to make models that generate more human-like text.

How it works:

#Users prompt an OpenAI, Anthropic, or Google model
#A set of instructions encourages the model to return a response using its typical patterns
#The program captures the model's response
#*The first response is saved as a JSONL file in a Google bucket
#*The first response is scored as an example of '''Bad'''' model behavior
#A new prompt forces the models to generate a second response with editorial corrections
#*The second response is saved as a JSONL file in a Google bucket
#*The second response is scored as an example of '''Good'''' model behavior
#The program then forces changes if the models violate the restrictions
#The final output then appears
#The '''Good''' and '''Bad''' examples will fine-tune a foundational model

=== 1.1 Who this is for ===
----
*Writers
*Editors
*Journalists
*Marketers
*Researchers
*Assisstants
*Analysts
*Data enthusiasts
*Software developers

=== 1.2 Setting Realistic Expectations ===
----
This is a generative AI application. However, it is also a data science experiment. While Righting Sentences is like many public genAI apps, it is not the same.

* Expect occasional bugs in the user interface.
* Expect some responses to be slower to generate because of the two-prompt system.
* Expect periodic odd sentence constructions, and expect to edit the text.

The application is under continuous development.

=== 1.3 Warnings ===
----
Like other genAI apps, Righting Sentences can make mistakes. Furthermore, word pairings might be incorrect because the application determined that the correct method violated its instructions. While this behavior is by design, it should not be considered production-ready.

* Do not rely on Righting Sentences as a guaranteed source of truth. Generative AI can make mistakes.
* Do not use this software to replace advice from a doctor, lawyer, electrician, or other relevant professional.
* Do not use this software to generate content straight to production.

== 2. Getting Started ==

=== 2.1 Google Authentication ===
----
To use the application, you will need to sign in using the Google account associated with this project.

# Navigate to https://righting-sentences-573737403792.us-east1.run.app/
# Select '''Sign in with Google'''
# Enter the ''Username'' and ''Password'' for the Google account associated with this project
# Click '''Continue''' to accept the Terms of Service

You will be at the application's main screen.

== 3. Left Sidebar ==

The left sidebar contains:
* Your chat history
* The model selector
* A menu for app functions

To access each collapsed section:
* Hover the cursor over the ''Model'' selector to reveal the model selector and '''New Chat''' button
* Hover the cursor over the ''Menu'' to reveal '''Account''', '''Settings''', '''Help''', and '''Sign Out''' options

=== 3.0.1 Open and Close the Sidebar ===
* To close: select the '''X''' at the top right of the sidebar
* To open: select the hamburger menu (☰) at the top left

== 3.1 Chat History and Controls ==

=== 3.1.1 Chat history list ===
Each row in the chat history list shows:
* The conversation title
* The model used

To open a conversation:
# Navigate to the left sidebar
# Select the desired conversation

=== 3.1.2 Delete a conversation ===
To delete a conversation:
# Navigate to the chat history list.
# Select the trash icon at the far right of the conversation row.

Notes:
* Deleting a conversation removes it from your chat history.
* Uploaded files attached to that conversation are deleted as part of conversation deletion (best-effort).

== 4.2 Applying Settings ==
====4.2.2 Color====
----
Righting Sentences offers nine theme colors. The default color is '''Blue'''. Other color selections are:
*Purple
*Pink
*Red
*Orange
*Yellow
*Green
*Teal
*Cyan

Selecting a new color changes the buttons, the user conversation bubble, and the outline of various page elements across the platform.

====4.2.2 Custom Instructions====
----
====4.2.3 Model Instructions====
----

== 4.3 Model Selector ==
The model selector controls which model is used for a new conversation.

=== 4.3.1 Select a model ===
# Navigate to the model selector in the left sidebar.
# Select the model you want.
# Select '''New Chat''' to start a conversation using that model.

=== 4.3.2 Important: models cannot be changed mid-chat ===
Once a conversation has messages, the model selector is disabled for that conversation.

To change models:
# Select '''New Chat'''.
# Select a different model.
# Continue in the new conversation.

=== 4.3.3 Available models ===
The model list can change over time. Typical configured models include:
{| class="wikitable"
! Provider !! Example model names !! Notes
|-
| OpenAI || gpt-4o; gpt-5.2-pro || Used for general writing assistance and editing.
|-
| Anthropic || claude-sonnet-4-5-20250929 || Used for alternative writing style and reasoning.
|-
| Google || gemini-3-flash-preview || Used for fast drafting and variations.
|}

== 4.3 Main Chat Window ==
The main chat window contains:
* The header (conversation title and model indicator).
* The message transcript.
* The message input box and file upload controls.

=== 4.3.1 Header ===
The header shows:
* The conversation title (center/left)
* The current model badge (top right)

=== 4.3.2 Messages ===
Messages appear as bubbles:
* Your messages are on the right.
* Assistant messages are on the left.

Assistant messages can include formatting such as:
* bullet lists
* headings
* code blocks

=== 4.3.3 Copy assistant output ===
Each assistant message includes a copy control:
# Navigate to the assistant message you want.
# Hover the message bubble.
# Select the copy control at the bottom-right of the bubble.

== 5. Writing and Editing Workflow ==
== 5.1 How to ask for what you want ==
GenAI performs best when you provide clear context and constraints.

Recommended prompt pattern:
* What you are writing (email, report, press release, article, résumé).
* Your audience (customer, internal team, general public).
* Desired tone (formal, neutral, friendly, direct).
* Length constraints (e.g., “under 150 words”).
* Required content (facts, names, dates).

Example:
<pre>
Rewrite the following paragraph for a general audience. Keep it under 120 words and use a neutral tone:
...
</pre>

== 5.2 What responses should look like ==
The assistant should typically return:
* A polished version of your text, and/or
* Clearly labeled alternatives (Option A, Option B), and/or
* A short explanation of major edits (when helpful).

If the assistant output is not what you want:
* Select a specific change (tone, length, structure).
* Ask for a second version rather than editing line-by-line.

== 5.3 Editorial behavior (two-pass system) ==
Righting Sentences uses an editorial process designed to reduce “AI-sounding” language.

What you may notice:
* Responses may be rewritten to sound more natural and human.
* Some words or phrasing patterns may be avoided by design.

== 6. File Uploads ==
You can upload files to a conversation so the assistant can reference them when responding.

=== 6.1 Upload a file ===
# Navigate to the message input area.
# Select '''Upload'''.
# Select one or more files.

After upload:
* Files appear as “chips” above the input box.
* If the file can be parsed, it may show a “Parsed” status.

=== 6.2 Remove an uploaded file ===
# Navigate to the file chip above the message box.
# Select the remove (×) control on the chip.
Removing a file deletes it from the conversation’s context, so the assistant will no longer reference it.

=== 6.3 Supported file types ===
The application is designed to accept:
* Text: .txt, .md, .csv, .tsv, .json
* Documents: .pdf, .doc, .docx
* Presentations: .ppt, .pptx
* Spreadsheets: .xls, .xlsx
* Images: .png, .jpg/.jpeg, .gif, .webp, .bmp, .tiff

Notes:
* Parsing quality varies by file type and content.
* Very large or image-heavy documents may be partially parsed.

=== 6.4 File size limits ===
The default maximum upload size is 25 MB per file (configurable by the administrator).

=== 6.5 How uploaded files are used by the model ===
If a file is successfully parsed, the extracted text is attached to the conversation context so the model can reference it when answering your questions.

Tip:
* Ask questions that cite the file: “In the uploaded document, what are the main recommendations?”
* If the assistant says it cannot see the file, re-upload a text-friendly version or paste key sections into the chat.

== 7. Settings ==
Navigate to '''Settings''' from the left sidebar menu.

=== 7.1 Theme ===
Select a theme:
* '''Light'''
* '''Dark'''
* '''System''' (matches your OS preference)

=== 7.2 Primary color ===
Select a primary color to change accent styling (borders, icons, buttons).

=== 7.3 Custom instructions ===
Use '''Custom Instructions''' to provide information about your preferences (tone, style, constraints).

=== 7.4 LLM instructions ===
Use '''LLM Instructions''' to specify global rules for how the assistant should respond.

== 8. Account ==
Navigate to '''Account''' from the left sidebar menu.

The account page shows:
* Your Google profile photo (when available)
* Your name and email
* A '''Sign Out''' button

== 9. Data Storage, Privacy, and Access ==
=== 9.1 What is stored ===
The system stores:
* Conversations and messages (including your prompts and assistant responses)
* Uploaded files and file metadata
* Optional research logs for the editorial system (when enabled)

Because this is a data science project, assume that your prompts, responses, and uploaded content may be reviewed by the project administrator for research and quality improvement.

=== 9.2 Where data is stored ===
Data is stored in Google Cloud services:
* Conversation metadata and message content are stored in Google Cloud Firestore.
* Uploaded file objects are stored in Google Cloud Storage in a private bucket in the project’s Google Cloud environment.

=== 9.3 Who can access data ===
Data access is restricted to:
* The project owner and administrators for the underlying Google Cloud project (Saxton Publishing).

=== 9.4 Third-party model providers ===
When you send a message, the conversation content may be transmitted to the selected model provider to generate a response.

When you upload a file:
* Text may be extracted locally for common formats.
* In some cases (especially images), file content may be sent to a model provider for extraction (OCR/parsing) depending on configuration.

== 10. Troubleshooting ==
=== 10.1 I cannot sign in ===
* Confirm you are using a Google account.
* Confirm your account has been invited.
* If the problem persists, contact Saxton Publishing.

=== 10.2 I cannot change the model ===
This is expected once a conversation has messages.

To change models:
# Select '''New Chat'''.
# Select a different model.

=== 10.3 My file upload fails ===
If you see an upload error:
* The storage bucket may not be configured or may not exist.
* The server may not have permission to write to storage.

Contact the administrator with the exact error message.

=== 10.4 The assistant says it cannot access my file ===
* Confirm the file chip is visible above the message box.
* Upload a smaller version of the file, or a text-based export (for example, export a Word doc to .txt).
* For scanned PDFs or images, upload a clearer image or provide the text in the chat.

Righting Sentences - User Guide

2026-01-28T00:29:20Z

Saxtonmd77: /* 3. Left Sidebar */

=Righting Sentences User Guide=

Last updated: January 2026

Production URL: https://righting-sentences-573737403792.us-east1.run.app/

GitHub Project: https://github.com/saxtonmd/righting-sentences

Current version: 3.0.4

==Desktop user interface==
[[Image: Righting-Sentences-Desktop-Light.png|800px]]

==Mobile User Interface==
[[Image: Righting-Sentences-Mobile-Light.-3.0.4.png|300px]]

__TOC__

== 1. Purpose and Scope ==
'''Righting Sentences''' is a web-based chat application that generates better sentences from generative AI models. Prompts provide instructions to the models. The models then respond. Responses are expected to be more like standard written English. This means they should not contain repetitive triads, em dashes, or many words that genAI models frequently use. The goal is to make models that generate more human-like text.

How it works:

#Users prompt an OpenAI, Anthropic, or Google model
#A set of instructions encourages the model to return a response using its typical patterns
#The program captures the model's response
#*The first response is saved as a JSONL file in a Google bucket
#*The first response is scored as an example of '''Bad'''' model behavior
#A new prompt forces the models to generate a second response with editorial corrections
#*The second response is saved as a JSONL file in a Google bucket
#*The second response is scored as an example of '''Good'''' model behavior
#The program then forces changes if the models violate the restrictions
#The final output then appears
#The '''Good''' and '''Bad''' examples will fine-tune a foundational model

=== 1.1 Who this is for ===
----
*Writers
*Editors
*Journalists
*Marketers
*Researchers
*Assisstants
*Analysts
*Data enthusiasts
*Software developers

=== 1.2 Setting Realistic Expectations ===
----
This is a generative AI application. However, it is also a data science experiment. While Righting Sentences is like many public genAI apps, it is not the same.

* Expect occasional bugs in the user interface.
* Expect some responses to be slower to generate because of the two-prompt system.
* Expect periodic odd sentence constructions, and expect to edit the text.

The application is under continuous development.

=== 1.3 Warnings ===
----
Like other genAI apps, Righting Sentences can make mistakes. Furthermore, word pairings might be incorrect because the application determined that the correct method violated its instructions. While this behavior is by design, it should not be considered production-ready.

* Do not rely on Righting Sentences as a guaranteed source of truth. Generative AI can make mistakes.
* Do not use this software to replace advice from a doctor, lawyer, electrician, or other relevant professional.
* Do not use this software to generate content straight to production.

== 2. Getting Started ==

=== 2.1 Google Authentication ===
----
To use the application, you will need to sign in using the Google account associated with this project.

# Navigate to https://righting-sentences-573737403792.us-east1.run.app/
# Select '''Sign in with Google'''
# Enter the ''Username'' and ''Password'' for the Google account associated with this project
# Click '''Continue''' to accept the Terms of Service

You will be at the application's main screen.

== 3. Left Sidebar ==

The left sidebar contains:
* Your chat history
* The model selector
* A menu for app functions

To access each collapsed section:
* Hover the cursor over the ''Model'' selector to reveal the model selector and '''New Chat''' button
* Hover the cursor over the ''Menu'' to reveal '''Account''', '''Settings''', '''Help''', and '''Sign Out''' options

=== 3.0.1 Open and Close the Sidebar ===
* To close: select the '''X''' at the top right of the sidebar
* To open: select the hamburger menu (☰) at the top left

== 3.1 Chat History and Controls ==

=== 3.1.1 Chat history list ===
Each row in the chat history list shows:
* The conversation title
* The model used for that conversation

To open a conversation:
# Navigate to the left sidebar.
# Select the conversation you want.

=== 3.1.2 Delete a conversation ===
To delete a conversation:
# Navigate to the chat history list.
# Select the trash icon at the far right of the conversation row.

Notes:
* Deleting a conversation removes it from your chat history.
* Uploaded files attached to that conversation are deleted as part of conversation deletion (best-effort).

== 4.2 Applying Settings ==
====4.2.2 Color====
----
Righting Sentences offers nine theme colors. The default color is '''Blue'''. Other color selections are:
*Purple
*Pink
*Red
*Orange
*Yellow
*Green
*Teal
*Cyan

Selecting a new color changes the buttons, the user conversation bubble, and the outline of various page elements across the platform.

====4.2.2 Custom Instructions====
----
====4.2.3 Model Instructions====
----

== 4.3 Model Selector ==
The model selector controls which model is used for a new conversation.

=== 4.3.1 Select a model ===
# Navigate to the model selector in the left sidebar.
# Select the model you want.
# Select '''New Chat''' to start a conversation using that model.

=== 4.3.2 Important: models cannot be changed mid-chat ===
Once a conversation has messages, the model selector is disabled for that conversation.

To change models:
# Select '''New Chat'''.
# Select a different model.
# Continue in the new conversation.

=== 4.3.3 Available models ===
The model list can change over time. Typical configured models include:
{| class="wikitable"
! Provider !! Example model names !! Notes
|-
| OpenAI || gpt-4o; gpt-5.2-pro || Used for general writing assistance and editing.
|-
| Anthropic || claude-sonnet-4-5-20250929 || Used for alternative writing style and reasoning.
|-
| Google || gemini-3-flash-preview || Used for fast drafting and variations.
|}

== 4.3 Main Chat Window ==
The main chat window contains:
* The header (conversation title and model indicator).
* The message transcript.
* The message input box and file upload controls.

=== 4.3.1 Header ===
The header shows:
* The conversation title (center/left)
* The current model badge (top right)

=== 4.3.2 Messages ===
Messages appear as bubbles:
* Your messages are on the right.
* Assistant messages are on the left.

Assistant messages can include formatting such as:
* bullet lists
* headings
* code blocks

=== 4.3.3 Copy assistant output ===
Each assistant message includes a copy control:
# Navigate to the assistant message you want.
# Hover the message bubble.
# Select the copy control at the bottom-right of the bubble.

== 5. Writing and Editing Workflow ==
== 5.1 How to ask for what you want ==
GenAI performs best when you provide clear context and constraints.

Recommended prompt pattern:
* What you are writing (email, report, press release, article, résumé).
* Your audience (customer, internal team, general public).
* Desired tone (formal, neutral, friendly, direct).
* Length constraints (e.g., “under 150 words”).
* Required content (facts, names, dates).

Example:
<pre>
Rewrite the following paragraph for a general audience. Keep it under 120 words and use a neutral tone:
...
</pre>

== 5.2 What responses should look like ==
The assistant should typically return:
* A polished version of your text, and/or
* Clearly labeled alternatives (Option A, Option B), and/or
* A short explanation of major edits (when helpful).

If the assistant output is not what you want:
* Select a specific change (tone, length, structure).
* Ask for a second version rather than editing line-by-line.

== 5.3 Editorial behavior (two-pass system) ==
Righting Sentences uses an editorial process designed to reduce “AI-sounding” language.

What you may notice:
* Responses may be rewritten to sound more natural and human.
* Some words or phrasing patterns may be avoided by design.

== 6. File Uploads ==
You can upload files to a conversation so the assistant can reference them when responding.

=== 6.1 Upload a file ===
# Navigate to the message input area.
# Select '''Upload'''.
# Select one or more files.

After upload:
* Files appear as “chips” above the input box.
* If the file can be parsed, it may show a “Parsed” status.

=== 6.2 Remove an uploaded file ===
# Navigate to the file chip above the message box.
# Select the remove (×) control on the chip.
Removing a file deletes it from the conversation’s context, so the assistant will no longer reference it.

=== 6.3 Supported file types ===
The application is designed to accept:
* Text: .txt, .md, .csv, .tsv, .json
* Documents: .pdf, .doc, .docx
* Presentations: .ppt, .pptx
* Spreadsheets: .xls, .xlsx
* Images: .png, .jpg/.jpeg, .gif, .webp, .bmp, .tiff

Notes:
* Parsing quality varies by file type and content.
* Very large or image-heavy documents may be partially parsed.

=== 6.4 File size limits ===
The default maximum upload size is 25 MB per file (configurable by the administrator).

=== 6.5 How uploaded files are used by the model ===
If a file is successfully parsed, the extracted text is attached to the conversation context so the model can reference it when answering your questions.

Tip:
* Ask questions that cite the file: “In the uploaded document, what are the main recommendations?”
* If the assistant says it cannot see the file, re-upload a text-friendly version or paste key sections into the chat.

== 7. Settings ==
Navigate to '''Settings''' from the left sidebar menu.

=== 7.1 Theme ===
Select a theme:
* '''Light'''
* '''Dark'''
* '''System''' (matches your OS preference)

=== 7.2 Primary color ===
Select a primary color to change accent styling (borders, icons, buttons).

=== 7.3 Custom instructions ===
Use '''Custom Instructions''' to provide information about your preferences (tone, style, constraints).

=== 7.4 LLM instructions ===
Use '''LLM Instructions''' to specify global rules for how the assistant should respond.

== 8. Account ==
Navigate to '''Account''' from the left sidebar menu.

The account page shows:
* Your Google profile photo (when available)
* Your name and email
* A '''Sign Out''' button

== 9. Data Storage, Privacy, and Access ==
=== 9.1 What is stored ===
The system stores:
* Conversations and messages (including your prompts and assistant responses)
* Uploaded files and file metadata
* Optional research logs for the editorial system (when enabled)

Because this is a data science project, assume that your prompts, responses, and uploaded content may be reviewed by the project administrator for research and quality improvement.

=== 9.2 Where data is stored ===
Data is stored in Google Cloud services:
* Conversation metadata and message content are stored in Google Cloud Firestore.
* Uploaded file objects are stored in Google Cloud Storage in a private bucket in the project’s Google Cloud environment.

=== 9.3 Who can access data ===
Data access is restricted to:
* The project owner and administrators for the underlying Google Cloud project (Saxton Publishing).

=== 9.4 Third-party model providers ===
When you send a message, the conversation content may be transmitted to the selected model provider to generate a response.

When you upload a file:
* Text may be extracted locally for common formats.
* In some cases (especially images), file content may be sent to a model provider for extraction (OCR/parsing) depending on configuration.

== 10. Troubleshooting ==
=== 10.1 I cannot sign in ===
* Confirm you are using a Google account.
* Confirm your account has been invited.
* If the problem persists, contact Saxton Publishing.

=== 10.2 I cannot change the model ===
This is expected once a conversation has messages.

To change models:
# Select '''New Chat'''.
# Select a different model.

=== 10.3 My file upload fails ===
If you see an upload error:
* The storage bucket may not be configured or may not exist.
* The server may not have permission to write to storage.

Contact the administrator with the exact error message.

=== 10.4 The assistant says it cannot access my file ===
* Confirm the file chip is visible above the message box.
* Upload a smaller version of the file, or a text-based export (for example, export a Word doc to .txt).
* For scanned PDFs or images, upload a clearer image or provide the text in the chat.

Righting Sentences - User Guide

2026-01-27T22:39:21Z

Saxtonmd77: /* 3. Left Sidebar */

=Righting Sentences User Guide=

Last updated: January 2026

Production URL: https://righting-sentences-573737403792.us-east1.run.app/

GitHub Project: https://github.com/saxtonmd/righting-sentences

Current version: 3.0.4

==Desktop user interface==
[[Image: Righting-Sentences-Desktop-Light.png|800px]]

==Mobile User Interface==
[[Image: Righting-Sentences-Mobile-Light.-3.0.4.png|300px]]

__TOC__

== 1. Purpose and Scope ==
'''Righting Sentences''' is a web-based chat application that generates better sentences from generative AI models. Prompts provide instructions to the models. The models then respond. Responses are expected to be more like standard written English. This means they should not contain repetitive triads, em dashes, or many words that genAI models frequently use. The goal is to make models that generate more human-like text.

How it works:

#Users prompt an OpenAI, Anthropic, or Google model
#A set of instructions encourages the model to return a response using its typical patterns
#The program captures the model's response
#*The first response is saved as a JSONL file in a Google bucket
#*The first response is scored as an example of '''Bad'''' model behavior
#A new prompt forces the models to generate a second response with editorial corrections
#*The second response is saved as a JSONL file in a Google bucket
#*The second response is scored as an example of '''Good'''' model behavior
#The program then forces changes if the models violate the restrictions
#The final output then appears
#The '''Good''' and '''Bad''' examples will fine-tune a foundational model

=== 1.1 Who this is for ===
----
*Writers
*Editors
*Journalists
*Marketers
*Researchers
*Assisstants
*Analysts
*Data enthusiasts
*Software developers

=== 1.2 Setting Realistic Expectations ===
----
This is a generative AI application. However, it is also a data science experiment. While Righting Sentences is like many public genAI apps, it is not the same.

* Expect occasional bugs in the user interface.
* Expect some responses to be slower to generate because of the two-prompt system.
* Expect periodic odd sentence constructions, and expect to edit the text.

The application is under continuous development.

=== 1.3 Warnings ===
----
Like other genAI apps, Righting Sentences can make mistakes. Furthermore, word pairings might be incorrect because the application determined that the correct method violated its instructions. While this behavior is by design, it should not be considered production-ready.

* Do not rely on Righting Sentences as a guaranteed source of truth. Generative AI can make mistakes.
* Do not use this software to replace advice from a doctor, lawyer, electrician, or other relevant professional.
* Do not use this software to generate content straight to production.

== 2. Getting Started ==

=== 2.1 Google Authentication ===
----
To use the application, you will need to sign in using the Google account associated with this project.

# Navigate to https://righting-sentences-573737403792.us-east1.run.app/
# Select '''Sign in with Google'''
# Enter the ''Username'' and ''Password'' for the Google account associated with this project
# Click '''Continue''' to accept the Terms of Service

You will be at the application's main screen.

== 3. Left Sidebar ==

The left sidebar contains:
* Your chat history
* The model selector
* A menu for app functions

To access each collapsed section:
* Hover yor cursor over the ''Model'' selector to reveal the model selector and '''New Chat''' button
* Hover your cursor over the ''Menu'' to reveal '''Account''', '''Settings''', '''Help''', and '''Sign Out''' options

=== 3.0.1 Open and Close the Sidebar ===
* To close: select the '''X''' at the top right of the sidebar
* To open: select the hamburger menu (☰) at the top left

== 3.1 Chat History and Controls ==

=== 3.1.1 Chat history list ===
Each row in the chat history list shows:
* The conversation title
* The model used for that conversation

To open a conversation:
# Navigate to the left sidebar.
# Select the conversation you want.

=== 3.1.2 Delete a conversation ===
To delete a conversation:
# Navigate to the chat history list.
# Select the trash icon at the far right of the conversation row.

Notes:
* Deleting a conversation removes it from your chat history.
* Uploaded files attached to that conversation are deleted as part of conversation deletion (best-effort).

== 4.2 Applying Settings ==
====4.2.2 Color====
----
Righting Sentences offers nine theme colors. The default color is '''Blue'''. Other color selections are:
*Purple
*Pink
*Red
*Orange
*Yellow
*Green
*Teal
*Cyan

Selecting a new color changes the buttons, the user conversation bubble, and the outline of various page elements across the platform.

====4.2.2 Custom Instructions====
----
====4.2.3 Model Instructions====
----

== 4.3 Model Selector ==
The model selector controls which model is used for a new conversation.

=== 4.3.1 Select a model ===
# Navigate to the model selector in the left sidebar.
# Select the model you want.
# Select '''New Chat''' to start a conversation using that model.

=== 4.3.2 Important: models cannot be changed mid-chat ===
Once a conversation has messages, the model selector is disabled for that conversation.

To change models:
# Select '''New Chat'''.
# Select a different model.
# Continue in the new conversation.

=== 4.3.3 Available models ===
The model list can change over time. Typical configured models include:
{| class="wikitable"
! Provider !! Example model names !! Notes
|-
| OpenAI || gpt-4o; gpt-5.2-pro || Used for general writing assistance and editing.
|-
| Anthropic || claude-sonnet-4-5-20250929 || Used for alternative writing style and reasoning.
|-
| Google || gemini-3-flash-preview || Used for fast drafting and variations.
|}

== 4.3 Main Chat Window ==
The main chat window contains:
* The header (conversation title and model indicator).
* The message transcript.
* The message input box and file upload controls.

=== 4.3.1 Header ===
The header shows:
* The conversation title (center/left)
* The current model badge (top right)

=== 4.3.2 Messages ===
Messages appear as bubbles:
* Your messages are on the right.
* Assistant messages are on the left.

Assistant messages can include formatting such as:
* bullet lists
* headings
* code blocks

=== 4.3.3 Copy assistant output ===
Each assistant message includes a copy control:
# Navigate to the assistant message you want.
# Hover the message bubble.
# Select the copy control at the bottom-right of the bubble.

== 5. Writing and Editing Workflow ==
== 5.1 How to ask for what you want ==
GenAI performs best when you provide clear context and constraints.

Recommended prompt pattern:
* What you are writing (email, report, press release, article, résumé).
* Your audience (customer, internal team, general public).
* Desired tone (formal, neutral, friendly, direct).
* Length constraints (e.g., “under 150 words”).
* Required content (facts, names, dates).

Example:
<pre>
Rewrite the following paragraph for a general audience. Keep it under 120 words and use a neutral tone:
...
</pre>

== 5.2 What responses should look like ==
The assistant should typically return:
* A polished version of your text, and/or
* Clearly labeled alternatives (Option A, Option B), and/or
* A short explanation of major edits (when helpful).

If the assistant output is not what you want:
* Select a specific change (tone, length, structure).
* Ask for a second version rather than editing line-by-line.

== 5.3 Editorial behavior (two-pass system) ==
Righting Sentences uses an editorial process designed to reduce “AI-sounding” language.

What you may notice:
* Responses may be rewritten to sound more natural and human.
* Some words or phrasing patterns may be avoided by design.

== 6. File Uploads ==
You can upload files to a conversation so the assistant can reference them when responding.

=== 6.1 Upload a file ===
# Navigate to the message input area.
# Select '''Upload'''.
# Select one or more files.

After upload:
* Files appear as “chips” above the input box.
* If the file can be parsed, it may show a “Parsed” status.

=== 6.2 Remove an uploaded file ===
# Navigate to the file chip above the message box.
# Select the remove (×) control on the chip.
Removing a file deletes it from the conversation’s context, so the assistant will no longer reference it.

=== 6.3 Supported file types ===
The application is designed to accept:
* Text: .txt, .md, .csv, .tsv, .json
* Documents: .pdf, .doc, .docx
* Presentations: .ppt, .pptx
* Spreadsheets: .xls, .xlsx
* Images: .png, .jpg/.jpeg, .gif, .webp, .bmp, .tiff

Notes:
* Parsing quality varies by file type and content.
* Very large or image-heavy documents may be partially parsed.

=== 6.4 File size limits ===
The default maximum upload size is 25 MB per file (configurable by the administrator).

=== 6.5 How uploaded files are used by the model ===
If a file is successfully parsed, the extracted text is attached to the conversation context so the model can reference it when answering your questions.

Tip:
* Ask questions that cite the file: “In the uploaded document, what are the main recommendations?”
* If the assistant says it cannot see the file, re-upload a text-friendly version or paste key sections into the chat.

== 7. Settings ==
Navigate to '''Settings''' from the left sidebar menu.

=== 7.1 Theme ===
Select a theme:
* '''Light'''
* '''Dark'''
* '''System''' (matches your OS preference)

=== 7.2 Primary color ===
Select a primary color to change accent styling (borders, icons, buttons).

=== 7.3 Custom instructions ===
Use '''Custom Instructions''' to provide information about your preferences (tone, style, constraints).

=== 7.4 LLM instructions ===
Use '''LLM Instructions''' to specify global rules for how the assistant should respond.

== 8. Account ==
Navigate to '''Account''' from the left sidebar menu.

The account page shows:
* Your Google profile photo (when available)
* Your name and email
* A '''Sign Out''' button

== 9. Data Storage, Privacy, and Access ==
=== 9.1 What is stored ===
The system stores:
* Conversations and messages (including your prompts and assistant responses)
* Uploaded files and file metadata
* Optional research logs for the editorial system (when enabled)

Because this is a data science project, assume that your prompts, responses, and uploaded content may be reviewed by the project administrator for research and quality improvement.

=== 9.2 Where data is stored ===
Data is stored in Google Cloud services:
* Conversation metadata and message content are stored in Google Cloud Firestore.
* Uploaded file objects are stored in Google Cloud Storage in a private bucket in the project’s Google Cloud environment.

=== 9.3 Who can access data ===
Data access is restricted to:
* The project owner and administrators for the underlying Google Cloud project (Saxton Publishing).

=== 9.4 Third-party model providers ===
When you send a message, the conversation content may be transmitted to the selected model provider to generate a response.

When you upload a file:
* Text may be extracted locally for common formats.
* In some cases (especially images), file content may be sent to a model provider for extraction (OCR/parsing) depending on configuration.

== 10. Troubleshooting ==
=== 10.1 I cannot sign in ===
* Confirm you are using a Google account.
* Confirm your account has been invited.
* If the problem persists, contact Saxton Publishing.

=== 10.2 I cannot change the model ===
This is expected once a conversation has messages.

To change models:
# Select '''New Chat'''.
# Select a different model.

=== 10.3 My file upload fails ===
If you see an upload error:
* The storage bucket may not be configured or may not exist.
* The server may not have permission to write to storage.

Contact the administrator with the exact error message.

=== 10.4 The assistant says it cannot access my file ===
* Confirm the file chip is visible above the message box.
* Upload a smaller version of the file, or a text-based export (for example, export a Word doc to .txt).
* For scanned PDFs or images, upload a clearer image or provide the text in the chat.

Righting Sentences - User Guide

2026-01-27T20:30:32Z

Saxtonmd77: /* 3. Left Sidebar */

=Righting Sentences User Guide=

Last updated: January 2026

Production URL: https://righting-sentences-573737403792.us-east1.run.app/

GitHub Project: https://github.com/saxtonmd/righting-sentences

Current version: 3.0.4

==Desktop user interface==
[[Image: Righting-Sentences-Desktop-Light.png|800px]]

==Mobile User Interface==
[[Image: Righting-Sentences-Mobile-Light.-3.0.4.png|300px]]

__TOC__

== 1. Purpose and Scope ==
'''Righting Sentences''' is a web-based chat application that generates better sentences from generative AI models. Prompts provide instructions to the models. The models then respond. Responses are expected to be more like standard written English. This means they should not contain repetitive triads, em dashes, or many words that genAI models frequently use. The goal is to make models that generate more human-like text.

How it works:

#Users prompt an OpenAI, Anthropic, or Google model
#A set of instructions encourages the model to return a response using its typical patterns
#The program captures the model's response
#*The first response is saved as a JSONL file in a Google bucket
#*The first response is scored as an example of '''Bad'''' model behavior
#A new prompt forces the models to generate a second response with editorial corrections
#*The second response is saved as a JSONL file in a Google bucket
#*The second response is scored as an example of '''Good'''' model behavior
#The program then forces changes if the models violate the restrictions
#The final output then appears
#The '''Good''' and '''Bad''' examples will fine-tune a foundational model

=== 1.1 Who this is for ===
----
*Writers
*Editors
*Journalists
*Marketers
*Researchers
*Assisstants
*Analysts
*Data enthusiasts
*Software developers

=== 1.2 Setting Realistic Expectations ===
----
This is a generative AI application. However, it is also a data science experiment. While Righting Sentences is like many public genAI apps, it is not the same.

* Expect occasional bugs in the user interface.
* Expect some responses to be slower to generate because of the two-prompt system.
* Expect periodic odd sentence constructions, and expect to edit the text.

The application is under continuous development.

=== 1.3 Warnings ===
----
Like other genAI apps, Righting Sentences can make mistakes. Furthermore, word pairings might be incorrect because the application determined that the correct method violated its instructions. While this behavior is by design, it should not be considered production-ready.

* Do not rely on Righting Sentences as a guaranteed source of truth. Generative AI can make mistakes.
* Do not use this software to replace advice from a doctor, lawyer, electrician, or other relevant professional.
* Do not use this software to generate content straight to production.

== 2. Getting Started ==

=== 2.1 Google Authentication ===
----
To use the application, you will need to sign in using the Google account associated with this project.

# Navigate to https://righting-sentences-573737403792.us-east1.run.app/
# Select '''Sign in with Google'''
# Enter the ''Username'' and ''Password'' for the Google account associated with this project
# Click '''Continue''' to accept the Terms of Service

You will be at the application's main screen.

== 3. Left Sidebar ==

The left sidebar contains:
* A list of prior conversations (your chat history)
* A model selector (choose which GenAI model to use for a new chat)
* A '''New Chat''' button.
* A bottom menu with '''Account''', '''Settings''', '''Help''', and '''Sign Out'''

On desktop devices, users can keep the chat history list visible while collapsing the top and bottom controls.

To access each collapsed section:
* Hover over the '''Model''' button to reveal the model selector and '''New Chat''' button
* Select or hover over the '''Menu''' button to reveal '''Account''', '''Settings''', '''Help''', and '''Sign Out''' buttons

=== 3.0.1 Open and close the sidebar ===
* To close: select the '''X''' (close) button at the top of the sidebar.
* To open: select the hamburger menu (☰) in the main header.

== 3.1 Chat History and Controls ==

=== 3.1.1 Chat history list ===
Each row in the chat history list shows:
* The conversation title
* The model used for that conversation

To open a conversation:
# Navigate to the left sidebar.
# Select the conversation you want.

=== 3.1.2 Delete a conversation ===
To delete a conversation:
# Navigate to the chat history list.
# Select the trash icon at the far right of the conversation row.

Notes:
* Deleting a conversation removes it from your chat history.
* Uploaded files attached to that conversation are deleted as part of conversation deletion (best-effort).

== 4.2 Applying Settings ==
====4.2.2 Color====
----
Righting Sentences offers nine theme colors. The default color is '''Blue'''. Other color selections are:
*Purple
*Pink
*Red
*Orange
*Yellow
*Green
*Teal
*Cyan

Selecting a new color changes the buttons, the user conversation bubble, and the outline of various page elements across the platform.

====4.2.2 Custom Instructions====
----
====4.2.3 Model Instructions====
----

== 4.3 Model Selector ==
The model selector controls which model is used for a new conversation.

=== 4.3.1 Select a model ===
# Navigate to the model selector in the left sidebar.
# Select the model you want.
# Select '''New Chat''' to start a conversation using that model.

=== 4.3.2 Important: models cannot be changed mid-chat ===
Once a conversation has messages, the model selector is disabled for that conversation.

To change models:
# Select '''New Chat'''.
# Select a different model.
# Continue in the new conversation.

=== 4.3.3 Available models ===
The model list can change over time. Typical configured models include:
{| class="wikitable"
! Provider !! Example model names !! Notes
|-
| OpenAI || gpt-4o; gpt-5.2-pro || Used for general writing assistance and editing.
|-
| Anthropic || claude-sonnet-4-5-20250929 || Used for alternative writing style and reasoning.
|-
| Google || gemini-3-flash-preview || Used for fast drafting and variations.
|}

== 4.3 Main Chat Window ==
The main chat window contains:
* The header (conversation title and model indicator).
* The message transcript.
* The message input box and file upload controls.

=== 4.3.1 Header ===
The header shows:
* The conversation title (center/left)
* The current model badge (top right)

=== 4.3.2 Messages ===
Messages appear as bubbles:
* Your messages are on the right.
* Assistant messages are on the left.

Assistant messages can include formatting such as:
* bullet lists
* headings
* code blocks

=== 4.3.3 Copy assistant output ===
Each assistant message includes a copy control:
# Navigate to the assistant message you want.
# Hover the message bubble.
# Select the copy control at the bottom-right of the bubble.

== 5. Writing and Editing Workflow ==
== 5.1 How to ask for what you want ==
GenAI performs best when you provide clear context and constraints.

Recommended prompt pattern:
* What you are writing (email, report, press release, article, résumé).
* Your audience (customer, internal team, general public).
* Desired tone (formal, neutral, friendly, direct).
* Length constraints (e.g., “under 150 words”).
* Required content (facts, names, dates).

Example:
<pre>
Rewrite the following paragraph for a general audience. Keep it under 120 words and use a neutral tone:
...
</pre>

== 5.2 What responses should look like ==
The assistant should typically return:
* A polished version of your text, and/or
* Clearly labeled alternatives (Option A, Option B), and/or
* A short explanation of major edits (when helpful).

If the assistant output is not what you want:
* Select a specific change (tone, length, structure).
* Ask for a second version rather than editing line-by-line.

== 5.3 Editorial behavior (two-pass system) ==
Righting Sentences uses an editorial process designed to reduce “AI-sounding” language.

What you may notice:
* Responses may be rewritten to sound more natural and human.
* Some words or phrasing patterns may be avoided by design.

== 6. File Uploads ==
You can upload files to a conversation so the assistant can reference them when responding.

=== 6.1 Upload a file ===
# Navigate to the message input area.
# Select '''Upload'''.
# Select one or more files.

After upload:
* Files appear as “chips” above the input box.
* If the file can be parsed, it may show a “Parsed” status.

=== 6.2 Remove an uploaded file ===
# Navigate to the file chip above the message box.
# Select the remove (×) control on the chip.
Removing a file deletes it from the conversation’s context, so the assistant will no longer reference it.

=== 6.3 Supported file types ===
The application is designed to accept:
* Text: .txt, .md, .csv, .tsv, .json
* Documents: .pdf, .doc, .docx
* Presentations: .ppt, .pptx
* Spreadsheets: .xls, .xlsx
* Images: .png, .jpg/.jpeg, .gif, .webp, .bmp, .tiff

Notes:
* Parsing quality varies by file type and content.
* Very large or image-heavy documents may be partially parsed.

=== 6.4 File size limits ===
The default maximum upload size is 25 MB per file (configurable by the administrator).

=== 6.5 How uploaded files are used by the model ===
If a file is successfully parsed, the extracted text is attached to the conversation context so the model can reference it when answering your questions.

Tip:
* Ask questions that cite the file: “In the uploaded document, what are the main recommendations?”
* If the assistant says it cannot see the file, re-upload a text-friendly version or paste key sections into the chat.

== 7. Settings ==
Navigate to '''Settings''' from the left sidebar menu.

=== 7.1 Theme ===
Select a theme:
* '''Light'''
* '''Dark'''
* '''System''' (matches your OS preference)

=== 7.2 Primary color ===
Select a primary color to change accent styling (borders, icons, buttons).

=== 7.3 Custom instructions ===
Use '''Custom Instructions''' to provide information about your preferences (tone, style, constraints).

=== 7.4 LLM instructions ===
Use '''LLM Instructions''' to specify global rules for how the assistant should respond.

== 8. Account ==
Navigate to '''Account''' from the left sidebar menu.

The account page shows:
* Your Google profile photo (when available)
* Your name and email
* A '''Sign Out''' button

== 9. Data Storage, Privacy, and Access ==
=== 9.1 What is stored ===
The system stores:
* Conversations and messages (including your prompts and assistant responses)
* Uploaded files and file metadata
* Optional research logs for the editorial system (when enabled)

Because this is a data science project, assume that your prompts, responses, and uploaded content may be reviewed by the project administrator for research and quality improvement.

=== 9.2 Where data is stored ===
Data is stored in Google Cloud services:
* Conversation metadata and message content are stored in Google Cloud Firestore.
* Uploaded file objects are stored in Google Cloud Storage in a private bucket in the project’s Google Cloud environment.

=== 9.3 Who can access data ===
Data access is restricted to:
* The project owner and administrators for the underlying Google Cloud project (Saxton Publishing).

=== 9.4 Third-party model providers ===
When you send a message, the conversation content may be transmitted to the selected model provider to generate a response.

When you upload a file:
* Text may be extracted locally for common formats.
* In some cases (especially images), file content may be sent to a model provider for extraction (OCR/parsing) depending on configuration.

== 10. Troubleshooting ==
=== 10.1 I cannot sign in ===
* Confirm you are using a Google account.
* Confirm your account has been invited.
* If the problem persists, contact Saxton Publishing.

=== 10.2 I cannot change the model ===
This is expected once a conversation has messages.

To change models:
# Select '''New Chat'''.
# Select a different model.

=== 10.3 My file upload fails ===
If you see an upload error:
* The storage bucket may not be configured or may not exist.
* The server may not have permission to write to storage.

Contact the administrator with the exact error message.

=== 10.4 The assistant says it cannot access my file ===
* Confirm the file chip is visible above the message box.
* Upload a smaller version of the file, or a text-based export (for example, export a Word doc to .txt).
* For scanned PDFs or images, upload a clearer image or provide the text in the chat.