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

LLMOps Basic — 158: codify rollback triggers on `Benchmark scepticism rituals` — memo `698118 [158]`

Lesson 158: Benchmark scepticism rituals

Focus

Anchor this drill to one production LLM workflow—even hypothetical. Token Benchmark scepticism rituals:158 keeps neighbouring lessons differentiable.

Key ideas

Deep dive notebook

Synthetic drill artefacts

Red-team tableau

1. Actor **support_agent**
2. Injection `INJECT-183`
3. Detector `policy-tier-3` → pager `llmops-oncall-2`
4. Log fields `trace_id,tenant_id,redaction_tier`

Practice

Practice Simulate degraded retrieval once; capture user-facing fallback copy. — 158 Bump 25.