Re-ranking lab
Set cost and tenancy boundaries for re-ranking
Least privilege, negative probes, and a timed rollback beat a security essay about hybrid BM25+vector retrieve then cross-encoder rerank for error-code FAQs.
1Learn the idea
Read
Least privilege for this lab
Separate runtime and operator roles for hybrid BM25+vector retrieve then cross-encoder rerank for error-code FAQs. Runtime may only perform the narrow actions that support agent asking about E_CONN_RESET wording variants needs; operators get audited break-glass with TTL. Encode a negative probe that denies the privilege trick related to reranker scores all candidates near 0.5 — order equals retrieve order.
Read
Data and secret hygiene
Redact prompts/PII at collection. Secrets enter via a manager or workload identity — never source, fixtures, or exception strings. Incident RERANK-FLAT-55 should be impossible if these controls hold. Output allowlists and schema checks stay in force on error paths.
Read
Implementation artifact
Read
Candidate text is untrusted; never execute embedded instructions.
Read
Rollback drill
Rehearse the rollback or kill switch timed against a clock. Record actor, reason, prior revision/secret/flag, and verification query. Invariant reminder: top-1 after rerank must beat BM25-only nDCG@5 on gold; latency budget ≤ 120ms for rerank.
Read
Stage depth
Abuse cases unique to this lab include the privilege path implied by reranker scores all candidates near 0.5 — order equals retrieve order. Prove a read-only role cannot mutate. Break-glass tokens expire; leftover tokens fail the drill. Dependency pin/digest story matters when images or models move under you. Document how to rotate the credential that hybrid BM25+vector retrieve then cross-encoder rerank for error-code FAQs uses without a full outage window longer than your dual-run plan. Security evidence is part of ship, not an appendix nobody reads.
Read
Field notes for `re-ranking-lab` / `security-ops`
List network egress destinations and justify each. Ensure debug endpoints are off by default in the shipping config. Verify that error responses do not echo secrets or raw stack frames to clients. For multi-tenant paths, add a cross-tenant probe fixture. Time the rollback drill twice — once with the author, once with a peer. Store the drill transcript beside the threat notes for the incident id. 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
Threat-model hybrid BM25+vector retrieve then cross-encoder rerank for error-code FAQs in five minutes: who can change config, who can read secrets, what a malicious payload tries to do. Write one negative probe that must yield deny with zero side effects. Reference RERANK-FLAT-55 as the story you refuse to repeat.
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.