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

LLMOps Basic — 098: pair eval regressions on `Staging deploy realism` — memo `724487 [98]`

Lesson 098: Staging deploy realism

Focus

Document interfaces between retrieval, prompts, and policy engines. Token Staging deploy realism:98 keeps neighbouring lessons differentiable.

Key ideas

Deep dive notebook

Synthetic drill artefacts

Eval harness snippet

case_id: LO-16963
route: support_rag_v1
must_include_patterns:
  - "\[chunk_"
forbid_patterns:
  - "guaranteed SLA"
judge_profile: tempered_4

Practice

Practice Draft three eval assertions QA must pass before prompt promotion. — 98 Bump 32.