Re-ranking lab
Ship and explain the reversible re-ranker rollout
A second person can reproduce query 'connection reset while uploading' ranks doc:e-conn-reset #1 after rerank from a clean checkout and name the owner for RERANK-FLAT-55.
1Learn the idea
Read
Clean-room demo
From a fresh clone/directory, run the commands that prove query 'connection reset while uploading' ranks doc:e-conn-reset #1 after rerank. A second person plays support agent asking about E_CONN_RESET wording variants and follows your script without coaching. The demo includes limitations: what hybrid BM25+vector retrieve then cross-encoder rerank for error-code FAQs still will not do.
Read
Evidence pack
Bundle: contract snippet, passing tests, metric snapshot for nDCG@5 and rerank_ms p95, security negative probe, rollback note, owner name. Reference RERANK-FLAT-55 as the drill you rehearsed. If any item is missing, the ship gate fails even if the happy path dazzles.
Read
Implementation artifact
python eval_rerank.py --gold error_codes.jsonl --require-ndcg 0.78
Read
Ownership and next review
For Re-ranking lab, name the human who gets paged, the review date for thresholds, and the condition that triggers reevaluation. Endpoint POST /v1/search/rerank remains the production surface you operate for hybrid BM25+vector retrieve then cross-encoder rerank for error-code FAQs — not a slide. Keep RERANK-FLAT-55 in the handoff template so the next owner inherits the drill.
Read
Stage depth
After the peer demo, schedule the next threshold review date. File a short changelog that mentions RERANK-FLAT-55 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.
Read
Field notes for `re-ranking-lab` / `mastery-ship`
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 hybrid BM25+vector retrieve then cross-encoder rerank for error-code FAQs, the human stakeholder is support agent asking about E_CONN_RESET wording variants, and the incident id you design against is RERANK-FLAT-55. Re-state the oracle in your notes — query 'connection reset while uploading' ranks doc:e-conn-reset #1 after rerank — and keep the invariant visible: top-1 after rerank must beat BM25-only nDCG@5 on gold; latency budget ≤ 120ms for rerank. Track nDCG@5 and rerank_ms p95 as the scoreboard. Surface under change control: POST /v1/search/rerank. If you only have forty minutes, finish the fixture for reranker scores all candidates near 0.5 — order equals retrieve order before polishing UI. Promotion language stays ternary: promote, hold, or roll back based on evidence, not hope.
Go deeper
Before you start
Why this matters
Draft a two-minute demo script that proves query 'connection reset while uploading' ranks doc:e-conn-reset #1 after rerank from a clean directory. Include the failure rehearsal for reranker scores all candidates near 0.5 — order equals retrieve order and the rollback/owner line. If the script needs tribal knowledge, the lab is not shipped.
Related lessons
Check your understanding
Page assessment
Answer from memory. Completion is saved from this evidence, not from opening the next page.
All responses are required.