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

LLMOps Advanced — 037: quantify hallucination fallout on `Agent guardrail tabletops` — memo `283167 [37]`

Lesson 037: Agent guardrail tabletops

Focus

Anchor this drill to one production LLM workflow—even hypothetical. Token Agent guardrail tabletops:37 keeps neighbouring lessons differentiable.

Key ideas

Deep dive notebook

Synthetic drill artefacts

Logging contract

| Field | Retention |
|-------|-----------|
| trace_id | 23d |
| prompt_hash | policy-defined |
| completion_excerpt | 24h hot |

Mask tier `pii-v2` before persistence.

Practice

Practice Attach rollback steps if cost-per-request crosses your guardrail. — 37 Bump 31.