Step01
Pull PR Data
Connect to the GitHub API and pull every single pull request from a specific repository that you want to analyze.
IntermediateEngineering
How to Analyze GitHub PRs to Understand Engineering Effort with AI
Use the Jev AI model to cheaply and quickly cluster thousands of GitHub pull requests into thematic areas. This helps engineering and product leaders understand the breakdown of work between new features, tech debt, and maintenance.
Before you start
Tools used
- JevVisitJev
TypeSafe AI’s model for fast structured decisions, including choices, scores, and boolean probabilities.
- CodexVisitCodex
OpenAI's cloud-based AI software engineering agent that can execute code, run tests, and handle complex multi-file tasks autonomously.
- GeminiVisitGemini
Google AI assistant
Step by step
The workflow
Follow the sequence once, then adapt the prompts, checks, and handoffs to your own setup.
3 steps
Step02
Cluster PRs with Jev
Use Jev to compare candidate pairs of PRs and judge whether they address the same theme. Group related PRs using those results. For larger repositories, narrow the candidate pairs first so you do not need to compare every possible pair.
Example prompt
Are you working on the same thematic area or not?
This pairwise comparison method is highly effective for clustering related items without needing predefined categories.
Step03
Label the Clusters
Once the PRs are grouped into clusters, use a cheap and fast large language model (like Gemini Flash Lite) to examine the PRs in each cluster and assign a descriptive label (e.g., 'Infrastructure', 'New Feature', 'Bug Fixes').
Build your next product with ChatPRD
Turn an idea into a PRD, user stories, and a plan.
Keep building
Related workflows
intermediateContentJev
How to Analyze YouTube Comments for Audience Insights with AI
Quickly analyze thousands of YouTube comments for sentiment and new content ideas using the Jev AI model. This workflow helps creators turn audience feedback into actionable insights for their content strategy.
Open
advancedProductJevCodex
How to Build a Multi-Model AI Product Insights Engine
Create a powerful product insights engine by combining Jev with other LLMs. Use Jev for large-scale classification of customer feedback and development data, then apply reasoning models to analyze the structured output for deep insights.
Open
beginnerDesignCodex
How to Generate Unique and Usable SVG Icons with AI
Go beyond generic icon libraries by prompting an AI model to create custom, characterful SVG icons. This workflow shows how to get unique, well-designed icons for your projects by providing simple, clear descriptions.
Open
Start shipping
better products.
Join 100,000+ product managers who use ChatPRD to write better docs, align teams faster, and build products users love.
Free to start
No credit card
SOC 2 certified
Enterprise ready