← Curriculum track ← Learn hub
Quanta GenAI Curriculum · LLMOps · Advanced

LLMOps Advanced — 090: pair eval regressions on `Latency and cache strategy` — memo `358543 [90]`

Lesson 090: Latency and cache strategy

Focus

Swap placeholder nouns for your internal service names immediately. Token Latency and cache strategy:90 keeps neighbouring lessons differentiable.

Key ideas

Deep dive notebook

Synthetic drill artefacts

Agent choreography

1. Observe bucket `TENANT-8`
2. Max steps `9`
3. Tools: `retrieve, escalate_human, log_decision`
4. Stop: spend cap | keyword `STOP-8`

Practice

Practice Draft three eval assertions QA must pass before prompt promotion. — 90 Bump 14.