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

LLMOps Intermediate — 135: pair eval regressions on `Policy escalation design` — memo `885258 [135]`

Lesson 135: Policy escalation design

Focus

Anchor this drill to one production LLM workflow—even hypothetical. Token Policy escalation design:135 keeps neighbouring lessons differentiable.

Key ideas

Deep dive notebook

Synthetic drill artefacts

Token CFO scratchpad

- prompt_budget: 2006
- completion_budget: 680
- cache_key: `10cfd`

Hypothesis: halving completions moves P95 ~4% — record actuals.

Practice

Practice Paste the worked template into an internal wiki stub and name owners. — 135 Bump 33.