Righting Sentences - User Guide

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: 3.0.3

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. This service is a data science project. Your usage implies your understanding and agreement to your data being used to fine-tune a foundational AI model.

1.1 Who this is for

• Invited friends of Matt's who get free Generative AI for helping him test and report bugs.

1.2 Setting Realistic Expectations

• 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.
• Expect occasional bugs in the user interface.
• Expect some responses to be slower to generate because of a two-prompt system.
• Expect periodic odd sentence constructions, and expect to edit the text.

2. Getting Started

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 Pricing

Invited members do not pay for use.

3. Getting Started

3.1 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.

3.2 First-time layout

The interface has two main areas:

• The left sidebar (chat history and controls).
• The main chat window (conversation, message input, and file upload).

4.1 Left Sidebar (Chat History and Controls)

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.

4.1.0 Sidebar sections may collapse (desktop)

On desktop devices (mouse/trackpad), the sidebar can keep the chat history list visible while collapsing the top and bottom controls.

To access each collapsed section:

• Select or hover over the Model handle to reveal the model selector and New Chat controls.
• Select or hover over the Menu handle to reveal Account, Settings, Help, and Sign Out.

4.1.1 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.

4.1.2 Chat history list

Each row in the chat history list shows:

• The conversation title
• The model used for that conversation

To open a conversation:

1. Navigate to the left sidebar.
2. Select the conversation you want.

4.1.3 Delete a conversation

To delete a conversation:

1. Navigate to the chat history list.
2. 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 Model Selector

The model selector controls which model is used for a new conversation.

4.2.1 Select a model

1. Navigate to the model selector in the left sidebar.
2. Select the model you want.
3. Select New Chat to start a conversation using that model.

4.2.2 Important: models cannot be changed mid-chat

Once a conversation has messages, the model selector is disabled for that conversation.

To change models:

1. Select New Chat.
2. Select a different model.
3. Continue in the new conversation.

4.2.3 Available models

The model list can change over time. Typical configured models include:

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:

1. Navigate to the assistant message you want.
2. Hover the message bubble.
3. Select the copy control at the bottom-right of the bubble.

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:

Rewrite the following paragraph for a general audience. Keep it under 120 words and use a neutral tone:
...

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

1. Navigate to the message input area.
2. Select Upload.
3. 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

1. Navigate to the file chip above the message box.
2. 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:

1. Select New Chat.
2. 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.