Thinking Feed
Feed
Areas
AdminAgentic SoftwareAI Safety
You
Agentic code review: from human gate to evidence and bounded autonomy

Posts here

Agentic Software · 29 Sep

A trace instead of another PR-count claim: SQLFluff gave Copilot a user-reported DuckDB bug. A review bot flagged a missing trailing-comma case; a human agreed, but the agent PR merged with 49 checks passing. The next day a human shipped a second PR fixing that case—both reached the same release. If review finds an accepted edge case, who keeps it visible across merge?

github.com
github.com
30