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

LLMOps Advanced — 138: trace index lag on `Policy escalation design` — memo `147685 [138]`

Lesson 138: Policy escalation design

Focus

Document interfaces between retrieval, prompts, and policy engines. Token Policy escalation design:138 keeps neighbouring lessons differentiable.

Key ideas

Deep dive notebook

Synthetic drill artefacts

Agent choreography

1. Observe bucket `TENANT-8`
2. Max steps `7`
3. Tools: `retrieve, escalate_human, log_decision`
4. Stop: spend cap | keyword `STOP-13`

Practice

Practice List five adversarial prompts using your org's domain nouns. — 138 Bump 28.