Jump to content

Righting Sentences User Guide - 4.0: Difference between revisions

From Saxton Publishing Technical Documentation
Saxtonmd77 (talk | contribs)
Bureaucrats, Interface administrators, Administrators
216 edits
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..."
 
 
(17 intermediate revisions by the same user not shown)
Line 8: Line 8:


== 1. Purpose and Scope ==
== 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.
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.
 
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. Access and Authentication ==
Line 30: Line 16:


=== 2.2 Invitation-only access ===
=== 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).
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 ===
=== 2.3 Sign in ===
Line 56: Line 42:
==== Model selector ====
==== Model selector ====
Choose which AI model to use for new conversations:
Choose which AI model to use for new conversations:
* '''GPT-4o''' - OpenAI's capable general-purpose model
* '''GPT-4o''' - OpenAI's most famous model
* '''GPT-5.2 Pro''' - OpenAI's advanced reasoning model
* '''GPT-5.2 Pro''' - OpenAI's advanced reasoning model
* '''Claude Sonnet 4.5''' - Anthropic's balanced model
* '''Claude Sonnet 4.5''' - Anthropic's general model
* '''Gemini-3 Flash''' - Google's fast, efficient model
* '''Gemini-3 Flash''' - Google's fast model


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


==== Menu items ====
==== Menu items ====
Line 98: Line 84:
== 5. Options Menu ==
== 5. Options Menu ==


The '''Options''' button inside the message input provides access to:
The '''Options''' button inside the message input area provides access to:
* File uploads
* File uploads
* Prompt templates
* Prompt templates
Line 104: Line 90:


=== 5.1 Opening Options ===
=== 5.1 Opening Options ===
Click the '''Options''' button (three dots icon) to reveal the dropdown menu.
Click the '''Options''' button to reveal the dropdown menu.


== 6. File Uploads ==
== 6. File Uploads ==
Line 148: Line 134:
! Template !! Description
! Template !! Description
|-
|-
| Locations || Global offices and delivery centers page
| Locations || Global offices and delivery centers
|-
|-
| Services || Service overview with capabilities, proof, and outcomes
| Services || Service overview
|-
|-
| Industries || Industry overview or specialization page
| Industries || Industry overview or specialization page
|-
|-
| Leadership || Leadership team introduction and credibility
| Leadership || Leadership team
|-
|-
| Clients || Client portfolio and proof of impact
| Clients || Client portfolio
|}
|}


Line 163: Line 149:
! Template !! Description
! Template !! Description
|-
|-
| Case Study (PPT) || PowerPoint presentation structure (7 slides)
| Case Study (PPT) || PowerPoint, single-page case study
|-
|-
| Case Study (Website) || Web-optimized case study with metrics
| Case Study (Website) || SEO-optimized case study with KPIs
|}
|}


Line 191: Line 177:


=== 8.2 Using quick actions ===
=== 8.2 Using quick actions ===
# Ensure there is a previous assistant message in the conversation
# You must write a prompt and receive a message before you can run a quick action
# Click '''Options'''
# Click '''Options'''
# Select a quick action
# Select a quick action
# The action executes immediately (no additional prompt needed)
# 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 ==
== 9. Editorial Insights ==


The Insights dashboard shows your personal editorial analytics.
The Insights dashboard shows a user's editorial analytics.


=== 9.1 Accessing Insights ===
=== 9.1 Accessing Insights ===
Line 216: Line 197:


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


=== 9.4 Recent Corrections ===
=== 9.4 Recent Corrections ===
Line 226: Line 204:
== 10. Conversation Export ==
== 10. Conversation Export ==


Export your conversations for documentation or backup.
Export your conversations.


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


Line 249: Line 227:


=== 11.3 Custom instructions ===
=== 11.3 Custom instructions ===
Provide information about your preferences that the assistant should remember.
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 ===
=== 11.4 LLM instructions ===
Add rules for how the assistant should respond in all conversations.
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 ==
== 12. The Two-Pass Editorial System ==


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


=== 12.1 How it works ===
=== 12.1 How it works ===
# '''Pass 1:''' The AI generates a natural response
# '''Pass 1:''' The AI generates a typical response for LLM models
# '''Detection:''' The system identifies AI-typical patterns:
# '''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
# '''Pass 2:''' The AI regenerates with stricter guidelines
# '''Post-processing:''' Any remaining issues are cleaned programmatically
# '''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. Troubleshooting ==
Line 290: Line 253:


=== 13.3 Quick actions are not available ===
=== 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.
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 ===
=== 13.4 Template is not working ===
Line 315: Line 278:
=== 14.3 Third-party providers ===
=== 14.3 Third-party providers ===
Messages are sent to the selected model provider (OpenAI, Anthropic, or Google) to generate responses.
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


----
----

Latest revision as of 00:14, 7 February 2026

Righting Sentences — User Guide (v4.0)

Last updated: February 2026

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

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

  1. Navigate to the production URL
  2. Select Sign in with Google
  3. Complete Google authentication
  4. 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.

  • 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

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

  1. Type your message in the input field
  2. Press Enter or click Send
  3. 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

  1. Click Options
  2. Select Upload files
  3. 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

  1. Click Options
  2. Select a template from the list
  3. The template badge appears above the input
  4. Type your specific content or context
  5. Send your message

7.2 Available templates

Landing Pages

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

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

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

  1. You must write a prompt and receive a message before you can run a quick action
  2. Click Options
  3. Select a quick action
  4. The action executes using Gemini 3

9. Editorial Insights

The Insights dashboard shows a user's editorial analytics.

9.1 Accessing Insights

  1. Open the sidebar
  2. 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

  1. Open the conversation you want to export
  2. Click the Export button in the header
  3. Select Markdown or JSON
  4. 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

  1. Pass 1: The AI generates a typical response for LLM models
  2. Detection: The system identifies AI-typical patterns
  3. Pass 2: The AI regenerates with stricter guidelines
  4. 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.

Retrieved from "https://docs.saxtonpublishing.com/index.php?title=Righting_Sentences_User_Guide_-_4.0&oldid=217"