Claude Code team says AI writes ~90% of code: after 3 failed fix rounds, hand off to a human
minchoi · x · 2026-11-19
minchoi breaks down rule 5 of the Claude Code team's verification methodology: with 90% of code written and reviewed by Claude and no human reading every diff, failures decide what needs a person. Claude runs the checks and fixes what fails; after 3 failed rounds it stops and hands off.
Related event: Claude Code Team Says 90% of Its Code Is Written and Reviewed by Claude(4 posts)→
More from coding & agent
- From $180 first gig to $20k AI installs: two pricing plays for selling AI to mid-size firms — aryanXmahajan · 2026-11-19
- Claude Code verification rules: differential tests, REVIEW.md isolation, and mined rules — minchoi · 2026-11-19
- Claude Code rules: 3 failed fixes then a human, and checks a change can't edit — minchoi · 2026-11-19
- Property tests for invariants: throw thousands of generated inputs at rules that must never break — minchoi · 2026-11-19
- Give Claude a way to run the change, not just the tests: verify skill in .claude/skills/ — minchoi · 2026-11-19
- Claude Code team says Claude writes and reviews ~90% of their code, aided by 7 verification rules — minchoi · 2026-11-19