Retrospective

Reflect on what happened. Identify what blocked agent autonomy. Produce concrete improvements so the system gets better.

Not tied to sprints or calendars. Run a retro when there's something worth learning from: a feature shipped, an incident resolved, a pattern of failures, a project wrapped.

Core Question

What happened that an agent couldn't handle autonomously, and what's the cheapest fix so it can next time?

Process

1. Identify the trigger
2. Gather evidence
3. Analyze through the autonomy lens
4. Capture learnings
5. Create improvement tickets
6. Append to .tap/learnings.md