Build the first working lookup-and-store path

Code the narrow path that serves cost owner cutting duplicate GPT calls for Acme Corp FAQs: accept → authorize/normalize → call dependency → validate → record. Keep stages named so a trace can show which boundary passed. Success must emit evidence useful to hit_rate ∈ [0.25,0.55] and cross_tenant_hits == 0, not only a 200 with prose. Predict the observable for POST /v1/answer before running: paraphrase hit returns cached answer with cache=HIT; different tenant never hits.

Drive the path with recording fakes or local stubs. Assert call order and arguments. Idempotency keys or stable ids should keep retries from duplicating costly work where the product requires it. Product under test remains tenant-scoped semantic cache for repeated FAQ paraphrases — resist adding unrelated features mid-path.

For Semantic cache lab, paste the CLI/HTTP transcript beside your prediction for POST /v1/answer. If the oracle is unmet (paraphrase hit returns cached answer with cache=HIT; different tenant never hits), stop and debug this page; do not compensate with prompt folktales. Re-run once after a clean process start to catch hidden global state that would invalidate CACHE-XTENANT-2.

Performance sketch: measure local p95 for the fake-backed path so later regressions are obvious. Keep concurrency modest until failure-handling proves limits. Log a single structured event per success with request id, revision, and the evidence field behind hit_rate ∈ [0.25,0.55] and cross_tenant_hits == 0. Avoid hidden global caches in the happy path unless the lab is about caching — and even then key by tenant. If the path calls a model, pin model id in config and echo it in the response for auditability. Remember cost owner cutting duplicate GPT calls for Acme Corp FAQs experiences wall-clock time, not your debugger’s single-step comfort.

Prefer explicit function names over a single god-object handleRequest. Thread a correlation id from ingress to the last log line. When streaming, define what partial failure means before coding. Snapshot one successful response body in fixtures after redaction. If the path writes to a queue, assert message attributes in the fake. Stop adding retries on this page; that is the next concern. In this chapter the product is tenant-scoped semantic cache for repeated FAQ paraphrases, the human stakeholder is cost owner cutting duplicate GPT calls for Acme Corp FAQs, and the incident id you design against is CACHE-XTENANT-2. Re-state the oracle in your notes — paraphrase hit returns cached answer with cache=HIT; different tenant never hits — and keep the invariant visible: cache key includes tenant_id + policy_version; similarity ≥ 0.92 and risk≠high. Track hit_rate ∈ [0.25,0.55] and cross_tenant_hits == 0 as the scoreboard. Surface under change control: POST /v1/answer. If you only have forty minutes, finish the fixture for cross-tenant near-duplicate question returns Acme's private pricing blurb before polishing UI. Promotion language stays ternary: promote, hold, or roll back based on evidence, not hope.