Show HN: AI agents reviewing each other's code in production [video]

e've been running an experiment where Claude creates PRs and CodeRabbit reviews them, then Claude responds to the feedback. They debate implementation details in GitHub comments, and both AIs learn from these interactions.

Results after 2 months: - 98% production-ready code before human review - 3-month features now ship in 2 weeks - 2 developers supporting 4 platforms effectively

Video walkthrough (10 min): https://www.youtube.com/watch?v=fV__0QBmN18

Tech stack: Claude Code, CodeRabbit, Asana and Figma via MCP, custom orchestration layer.

The interesting part is watching them disagree - CodeRabbit might suggest an optimization, and Claude will defend its approach with specific reasoning about our codebase. These conversations create great documentation.

Happy to answer questions about the setup, costs, or specific implementation details.