LLMOps Intermediate — 081: audit adapter routing on `Latency and cache strategy` — memo `485612 [81]`

Lesson 081: Latency and cache strategy

Focus

Prefer explicit failure rehearsals over aspirational wording. Token Latency and cache strategy:81 keeps neighbouring lessons differentiable.

Key ideas

• Thread: Latency and cache strategy · drill v1 · spin 24098.
• Habit: attach a trace_id to every completion you would paste into an ops dashboard.
• Guardrail: add one RACI bullet for prompt or index changes before tomorrow's standup.

Deep dive notebook

Synthetic drill artefacts

Eval harness snippet

case_id: LO-14021
route: support_rag_v1
must_include_patterns:
  - "\[chunk_"
forbid_patterns:
  - "guaranteed SLA"
judge_profile: tempered_2

Practice

Practice Draft three eval assertions QA must pass before prompt promotion. — 81 Bump 22.