Claude Code team blog: verification loops let coding agents prove their work
minchoi · x · 2026-11-19
minchoi links the full Claude Code team blog (by Addy Osmani): 90% of their code is written and reviewed by Claude. Verification loops are the building block of delegation — without them you can run 1-2 Claudes, with them dozens or hundreds. Internal tests show a separate grader checking work against a rubric improved structured file generation success by up to 10 points, with the biggest gains on the hardest problems. Once-expensive verification (tests, benchmarks, specs, e2e runs) is now cheap for agents to generate, and results can feed back into hooks or CLAUDE.md rules to prevent repeat issues.
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