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

LLMOps Advanced — 114: pair eval regressions on `Domain adaptation levers` — memo `123892 [114]`

Lesson 114: Domain adaptation levers

Focus

Anchor this drill to one production LLM workflow—even hypothetical. Token Domain adaptation levers:114 keeps neighbouring lessons differentiable.

Key ideas

Deep dive notebook

Synthetic drill artefacts

Red-team tableau

1. Actor **contractor**
2. Injection `INJECT-504`
3. Detector `policy-tier-3` → pager `llmops-oncall-1`
4. Log fields `trace_id,tenant_id,redaction_tier`

Practice

Practice Simulate degraded retrieval once; capture user-facing fallback copy. — 114 Bump 8.