t1-p3-07authored2–4h
Operational runbook
requires: t1-p3-06
Spec
A one-page runbook covering what each dashboard metric means, what to do when confidence scores drop, and how to roll back a prompt or model change.
Why this matters
The rollback section is the one that matters. Prompt changes are deployments, and most teams have no way to undo one - so writing the procedure forces you to build the capability.
Verify
No result yet. Run `learn verify t1-p3-07` locally, or push to trigger CI.
artifact
unrun
judge
unrun
Rubric
# t1-p3-07 — Operational runbook
**Task:** A one-page runbook covering what each dashboard metric means, what to do when confidence scores drop, and how to roll back a prompt or model change.
**Strong:** Directly answers every one of the review questions below in the affirmative, with specific evidence from the actual work, not a restatement of the task.
- Could someone who did not build this follow the rollback procedure under pressure?
- Are thresholds concrete numbers rather than "if it looks wrong"?
**Passing but weak:** The deliverable exists and technically satisfies the spec, but is generic, restates the task instructions instead of engaging with them, or only partially addresses the review questions below.
**Fails:** The deliverable is missing, or engages with none of the review questions below - e.g. it describes what was built without explaining the reasoning the task actually asks for.