Canary and operate incident response

From a fresh clone/directory, run the commands that prove INC-RAG-CIT-2201: feature flag off in 8m; customer update sent; groundedness restored. A second person plays incident commander coordinating mitigate → communicate → verify and follows your script without coaching. The demo includes limitations: what correctness incident for invalid RAG citations (SEV2) still will not do.

Bundle: contract snippet, passing tests, metric snapshot for time_to_declare_m, time_to_mitigate_m, customer_update_sent, security negative probe, rollback note, owner name. Reference INC-RAG-CIT-2201 as the drill you rehearsed. If any item is missing, the ship gate fails even if the happy path dazzles.

For Incident response lab, name the human who gets paged, the review date for thresholds, and the condition that triggers reevaluation. Endpoint POST /v1/rag/answer remains the production surface you operate for correctness incident for invalid RAG citations (SEV2) — not a slide. Keep INC-RAG-CIT-2201 in the handoff template so the next owner inherits the drill.

After the peer demo, schedule the next threshold review date. File a short changelog that mentions INC-RAG-CIT-2201 and the control that addresses it. Archive the evidence pack where your team already stores launch records. Resist rewriting everything “for real production” in one weekend — operate this slice until the metrics bore you, then widen. Final self-check: if telemetry vanished, would you still know to hold? If yes, you learned the operating posture this lane teaches.

Trim the demo script until every command is necessary. Record a peer signature line: name, date UTC, pass/fail. File known limitations as bullets, not apologies. Link the evidence pack from the README. Schedule the next game day on a calendar, even if it is solo. Archive the branch tag or release digest you actually shipped. In this chapter the product is correctness incident for invalid RAG citations (SEV2), the human stakeholder is incident commander coordinating mitigate → communicate → verify, and the incident id you design against is INC-RAG-CIT-2201. Re-state the oracle in your notes — INC-RAG-CIT-2201: feature flag off in 8m; customer update sent; groundedness restored — and keep the invariant visible: declare early; preserve evidence; mitigation scoped; no blame in channel. Track time_to_declare_m, time_to_mitigate_m, customer_update_sent as the scoreboard. Surface under change control: POST /v1/rag/answer. If you only have forty minutes, finish the fixture for team debugs for an hour without declaring — customers keep seeing wrong policy cites before polishing UI. Promotion language stays ternary: promote, hold, or roll back based on evidence, not hope.