
An AI agent can finish a feature, pass the tests, and still leave behind unnecessary abstractions, misleading comments, or a README that no longer matches the product. Asking it to "check everything" gives it little guidance about what to investigate or what would count as proof.

I have a hard time trusting an AI coding agent to review code it just wrote.

Bold is a device for a reader, and an instruction file has two readers with nothing in common: one has an eye that stops on a marked line, the other receives the same characters in the same order 🧠