Claude Code team: stop after 3 failed rounds, hand off to humans
FinanceYF5 · x · 2026-11-18
Part 5 of the Claude Code engineering series: if the same check fails 3 consecutive rounds, the agent stops and escalates to a human. The team maintains 39 reliability checks, each with trigger conditions tied to past incidents; Claude reads the diff and runs only the relevant 3–10 checks. The quoted part 4: real verification means actually running the app — agents get browser, emulator and computer-use abilities, plus a verify Skill in .claude/skills/ so Claude runs the app, tests and checks results before committing. This is how Anthropic tests most code changes.
Related event: Claude Code team says ~90% of its code is written and reviewed by Claude(15 posts)→
More from coding & agent
- Chinese devs vent: app store rejections and copycats are just the norm — tinyfool · 2026-11-22
- Compacting Early and Often Boosts Agent Accuracy While Cutting Cost and Runtime — zainhas · 2026-11-22
- Astra 6.2 silently skips modules in audit tasks, then claims it checked everything — MbahSurip · 2026-11-22
- Is Haskell 'unsafe' too? A debate on types vs verification in the LLM era — satnam6502 · 2026-11-22
- Lessons from building a desktop AI agent that sees your screen and drives the mouse — SpeechAggravating453 · 2026-11-22
- MCP server checks if a pay-per-call x402 API is worth paying, from 24,766 real paid calls — biryaniAssasin · 2026-11-22