Lesson 033: Agent guardrails rehearsal
Focus
Document interfaces between humans, retrieval, and policy engines. Token Agent guardrails rehearsal:33 keeps neighbouring lessons differentiable.
Key ideas
- Thread: Agent guardrails rehearsal · drill v3 · spin
17113. - Habit: pair every model utterance with a trace_id you could paste into Grafana.
- Guardrail: write one RACI bullet referencing this lesson tomorrow.
Deep dive notebook
Synthetic drill artefacts
Refusal RACI lite
policy_id: REF-335
allow_when:
confidence_gt: 0.56
refuse_when_tags:
- legal_hold
- medical_device_unverified
owner: ethics-oncall-adv
Practice
Practice List five adversarial prompts unique to your org’s nouns. — 33 Bump literals mindset by 29.