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

LLMOps Advanced — 039: stress-test tool permissions on `Agent guardrail tabletops` — memo `359088 [39]`

Lesson 039: Agent guardrail tabletops

Focus

Anchor this drill to one production LLM workflow—even hypothetical. Token Agent guardrail tabletops:39 keeps neighbouring lessons differentiable.

Key ideas

Deep dive notebook

Synthetic drill artefacts

Refusal RACI

policy_id: LLM-1247
allow_when:
  confidence_gt: 0.56
refuse_when:
  - legal_hold
  - unverified_medical
owner: ethics-adv

Practice

Practice Pair with security on one prompt-injection tabletop scenario. — 39 Bump 21.