Capstone: ship a tiny AI app
Set release boundaries for the grounded café FAQ application
Least privilege, negative probes, and a timed rollback beat a security essay about grounded café FAQ app with validation, five-note retrieval, citations, tests, demo.
1Learn the idea
Read
Least privilege for this lab
Separate runtime and operator roles for grounded café FAQ app with validation, five-note retrieval, citations, tests, demo. Runtime may only perform the narrow actions that café ops lead answering hours/wifi/pets questions from a kiosk needs; operators get audited break-glass with TTL. Encode a negative probe that denies the privilege trick related to demo relies on personal .env and unreproducible notebook state.
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 CAP-CAFE-DEMO-01 should be impossible if these controls hold. Output allowlists and schema checks stay in force on error paths.
Read
Implementation artifact
Read
Notes reviewed offline; strip instruction-like lines on ingest.
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: unsupported questions abstain; every answer cites a note id; two-minute clean-room demo.
Read
Stage depth
Abuse cases unique to this lab include the privilege path implied by demo relies on personal .env and unreproducible notebook state. 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 grounded café FAQ app with validation, five-note retrieval, citations, tests, demo 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 `capstone-ship-it` / `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 grounded café FAQ app with validation, five-note retrieval, citations, tests, demo, the human stakeholder is café ops lead answering hours/wifi/pets questions from a kiosk, and the incident id you design against is CAP-CAFE-DEMO-01. Re-state the oracle in your notes — gold 5/5 cited + 3/3 abstain; demo under 120s from clean checkout — and keep the invariant visible: unsupported questions abstain; every answer cites a note id; two-minute clean-room demo. Track gold_pass and demo_seconds as the scoreboard. Surface under change control: CLI faq_ask. If you only have forty minutes, finish the fixture for demo relies on personal .env and unreproducible notebook state 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 grounded café FAQ app with validation, five-note retrieval, citations, tests, demo 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 CAP-CAFE-DEMO-01 as the story you refuse to repeat.
Capstone security gates are release blockers for grounded café FAQ app with validation, five-note retrieval, citations, tests, demo, not optional polish.
In the wild
See how this idea shows up as a product and a company — then come back to the lesson. Skills transfer across vendors.
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.