Mastery: ship checklist

Shipping is a decision backed by artifacts, not the moment a command succeeds. The candidate release must show a clean fixture run, aggregate unsafe action escape rate meeting zero unauthorized tool executions and at least 0.95 benign-request pass rate, a security regression run, telemetry from a staging probe, and a named rollback target. Record model, prompt or policy, data, fixture, and price versions so the evidence can be reproduced after dependencies change.

Use a canary or shadow path when live behavior can differ from fixtures. Compare the candidate with the baseline on identical slices. Promotion should be automatic only for reversible, low-risk changes; security boundary changes and outbound actions need human approval. Define rollback triggers before rollout. A dashboard turning red is not enough—write the exact query, evaluation window, minimum sample, and command or alias swap that restores service.

After promotion, watch the short-term burn rate and the slow quality signal. Verify that guardrail_decision_total receives candidate traffic, traces resolve, logs are redacted, and budget limits work. Close the release by linking evidence and assigning follow-up owners. If an incident occurs, deny the call, return a neutral response, and emit a redacted audit event. The lesson is mastered when another engineer can operate the system from the repository and runbook without oral history.

For mastery, assemble the release evidence and rehearse rollback. A teammate should be able to answer “what changed, what passed, what will page us, and how do we undo it?” from committed artifacts.

Assemble a release record containing candidate and baseline versions, fixture hash, policy and model versions, evaluation report, security result, staging probe trace, budget result, owner, and rollback target. Re-run the known regression a keyword filter passes harmless wording but the model emits refund_order with an attacker-controlled customer_id from a clean checkout or equivalent isolated environment. The evidence must show unsafe action escape rate satisfies zero unauthorized tool executions and at least 0.95 benign-request pass rate without suppressing failed slices.

Send a canary or shadow request and follow its trace from entry to final decision. Confirm guardrail_decision_total receives candidate traffic, redaction remains effective, and the alert points to an actionable runbook. State the rollback trigger with metric, threshold, window, and minimum sample. Then rehearse rollback using a fake alias, feature flag, or action adapter and prove the stable version resumes service.

Promotion requires a named approver for irreversible actions or authority changes. After release, watch fast reliability signals and slower quality/cost signals for the declared period. If the gate or live SLO fails, deny the call, return a neutral response, and emit a redacted audit event. Close only when another engineer can reproduce the evidence and execute rollback without oral instructions.