Mastery: ship checklist

From a fresh clone/directory, run the commands that prove fixture question produces 3 child spans; total latency attributes sum within 5% of root. A second person plays on-call engineer debugging a slow groundedness miss and follows your script without coaching. The demo includes limitations: what OpenTelemetry traces across retrieve → rerank → generate for support answers still will not do.

Bundle: contract snippet, passing tests, metric snapshot for trace_completeness ≥ 0.99 and p95_end_to_end_ms ≤ 2500, security negative probe, rollback note, owner name. Reference TRACE-ORPHAN-441 as the drill you rehearsed. If any item is missing, the ship gate fails even if the happy path dazzles.

For LLM tracing lab, name the human who gets paged, the review date for thresholds, and the condition that triggers reevaluation. Endpoint POST /v1/support/answer remains the production surface you operate for OpenTelemetry traces across retrieve → rerank → generate for support answers — not a slide. Keep TRACE-ORPHAN-441 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 TRACE-ORPHAN-441 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 OpenTelemetry traces across retrieve → rerank → generate for support answers, the human stakeholder is on-call engineer debugging a slow groundedness miss, and the incident id you design against is TRACE-ORPHAN-441. Re-state the oracle in your notes — fixture question produces 3 child spans; total latency attributes sum within 5% of root — and keep the invariant visible: every span carries trace_id + redacted attrs; prompts sampled ≤ 1%. Track trace_completeness ≥ 0.99 and p95_end_to_end_ms ≤ 2500 as the scoreboard. Surface under change control: POST /v1/support/answer. If you only have forty minutes, finish the fixture for missing parent context → orphan spans, cannot join retrieve to answer before polishing UI. Promotion language stays ternary: promote, hold, or roll back based on evidence, not hope.