How I Built a Post-Mortem Loop So My AI Coding Agent Stops Repeating Mistakes

Automated excerpt

An agent that makes new mistakes is learning. If the agent already passes the replay without the rule, the rule isn't teaching anything. Don't let the agent that failed write the rule Early on, I had the failing agent propose its own rule in the same context.

Selected automatically from source text; not independently written or fact-checked. Read the original for full context.