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

LLMOps Advanced — 136: codify rollback triggers on `Policy escalation design` — memo `669383 [136]`

Lesson 136: Policy escalation design

Focus

Anchor this drill to one production LLM workflow—even hypothetical. Token Policy escalation design:136 keeps neighbouring lessons differentiable.

Key ideas

Deep dive notebook

Synthetic drill artefacts

Logging contract

| Field | Retention |
|-------|-----------|
| trace_id | 17d |
| prompt_hash | policy-defined |
| completion_excerpt | 24h hot |

Mask tier `pii-v1` before persistence.

Practice

Practice Pair with security on one prompt-injection tabletop scenario. — 136 Bump 22.