Mastery: ship checklist

From a fresh clone/directory, run the commands that prove candidate prompt beats baseline on groundedness by ≥ 0.03 without latency regression > 10%. A second person plays ML engineer gating a prompt change before Friday release and follows your script without coaching. The demo includes limitations: what offline+online eval harness for grounded support answers still will not do.

Bundle: contract snippet, passing tests, metric snapshot for groundedness, citation_precision, p95_latency_ms, security negative probe, rollback note, owner name. Reference EVAL-LEAK-308 as the drill you rehearsed. If any item is missing, the ship gate fails even if the happy path dazzles.

For Eval metrics lab, name the human who gets paged, the review date for thresholds, and the condition that triggers reevaluation. Endpoint python -m eval.run --gold v12 remains the production surface you operate for offline+online eval harness for grounded support answers — not a slide. Keep EVAL-LEAK-308 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 EVAL-LEAK-308 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 offline+online eval harness for grounded support answers, the human stakeholder is ML engineer gating a prompt change before Friday release, and the incident id you design against is EVAL-LEAK-308. Re-state the oracle in your notes — candidate prompt beats baseline on groundedness by ≥ 0.03 without latency regression > 10% — and keep the invariant visible: release needs groundedness ≥ 0.88 and latency p95 ≤ 2.0s on fixed gold set v12. Track groundedness, citation_precision, p95_latency_ms as the scoreboard. Surface under change control: python -m eval.run --gold v12. If you only have forty minutes, finish the fixture for eval set leaked into few-shot examples — scores look perfect, prod drops before polishing UI. Promotion language stays ternary: promote, hold, or roll back based on evidence, not hope.