Chapter 12: Review

The obvious second reader is the agent itself, which is the worst choice.

Self-evaluation bias

An agent marking its own work gives itself too high a mark. It checks what it meant to build rather than what it built, and from the inside those look the same.

"Are you sure?" is a weak question, because you are asking the same mind, with the same assumptions in front of it, to find what those assumptions hid. Separate the checker from the author and the check starts to mean something.

Say it to your agent

“Don't mark this as done yourself. Write what you changed and how to check it into HANDOFF.md. I will give that file and the diff to a new session, and that session decides.”

The workshop

Name a word, or describe what you mean in everyday language.