Revision as of 19:28, 6 February 2026

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

template_registry.py - Template loading and resolution
editorial_insights.py - Statistics computation (pure functions, no DB deps)
rate_limiter.py - Request rate limiting
logging_config.py - Structured logging configuration
InsightsPage.jsx - Editorial insights UI component

Architecture

Templates defined in templates.md 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 editorial_logs collection

Testing Infrastructure

pytest configuration for backend tests
Vitest setup for frontend component testing
Development dependencies separated into requirements-dev.txt

Upgrade Notes

For Users

No action required. New features are available immediately after deployment.

For Administrators

The /templates endpoint is now available for template listing
The /insights 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.

@@ Line 38: / Line 38: @@
 === Editorial Insights ===
-A new dashboard showing your personal editorial analytics:
+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 your conversations
+* '''Top Violations''' - Most common AI patterns detected in conversations
-* '''Recent Corrections''' - Examples of recent editorial improvements
+* '''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.
+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 ===