Define the production target for service-level objectives

This lab builds AI support-answer service with 99.5% availability + TTFT SLO. The human in the loop is reliability owner gating releases on error budget. Scope is intentionally narrower than “make AI reliable”: you will prove one oracle — 3% provider timeout for 20m trips fast-burn; monthly budget math matches calc-budget.py — and one invariant — bad events include malformed upstream + timeout fallbacks; auth 4xx excluded. Record non-goals in your notes so a later change cannot silently expand authority. The incident mnemonic for the chapter is SLO-VANITY-200-18; design as if that ticket is already written and you are filling evidence.

Turn the oracle into a table: input fixture, expected observable, prohibited side effect, owner, latency/cost ceiling. Separate model taste from software correctness — transport, auth, parsing, and termination must be deterministic even when generated text varies. Primary metric family: slo:availability:ratio and burn_rate1h. Averages without a denominator or revision label do not gate release. Fake external dependencies in unit tests; live calls wait until fakes pass.

Before implementation, encode a failing check that would have caught HTTP 200 fallbacks counted as good while citations empty — vanity availability. That failure is the pedagogical north star for later pages: contracts reject it, happy path never performs it, validation asserts it, failure-handling contains it, observability detects it, security-ops prevents privilege tricks around it, and mastery replays it in a drill. Endpoint under study: POST /v1/support/answer.

Capacity note for planners: estimate peak demand on POST /v1/support/answer and the cost ceiling for a failed retry storm. Write the abort conditions — unbounded spend, cross-tenant leakage, or inability to roll back — before you enjoy the first green test. Prefer synthetic fixtures shaped like production over anonymized production dumps you cannot share in class. When you are tempted to widen scope, re-read the oracle (3% provider timeout for 20m trips fast-burn; monthly budget math matches calc-budget.py) and cut features that do not serve it. The teaching outcome is judgment under constraints: reliability owner gating releases on error budget gets a trustworthy control, not a kitchen-sink framework. Keep the language of release decisions: promote, hold, or roll back — never “see if it gets better.”

Decide what will live in version control on day one: fixtures, contract markdown, and a failing test name. Write the cost ceiling as a hard number with currency and period. If the lab involves clusters, name the non-prod context you will use and forbid prod kubecontexts in scripts. Capture the baseline metric once before changing code so later gains are comparative. Refuse tools that hide the request path behind magic macros until the oracle is green on fakes. Your README section for this page should be five lines or fewer and still falsifiable. In this chapter the product is AI support-answer service with 99.5% availability + TTFT SLO, the human stakeholder is reliability owner gating releases on error budget, and the incident id you design against is SLO-VANITY-200-18. Re-state the oracle in your notes — 3% provider timeout for 20m trips fast-burn; monthly budget math matches calc-budget.py — and keep the invariant visible: bad events include malformed upstream + timeout fallbacks; auth 4xx excluded. Track slo:availability:ratio and burn_rate1h as the scoreboard. Surface under change control: POST /v1/support/answer. If you only have forty minutes, finish the fixture for HTTP 200 fallbacks counted as good while citations empty — vanity availability before polishing UI. Promotion language stays ternary: promote, hold, or roll back based on evidence, not hope.