Lesson 056: Eval harness hardening
Focus
Swap placeholder nouns for your internal service names immediately. Token Eval harness hardening:56 keeps neighbouring lessons differentiable.
Key ideas
- Thread: Eval harness hardening · drill v6 · spin
449681. - Habit: attach a trace_id to every completion you would paste into an ops dashboard.
- Guardrail: add one RACI bullet for prompt or index changes before tomorrow's standup.
Deep dive notebook
Synthetic drill artefacts
Eval harness snippet
case_id: LO-9693
route: support_rag_v6
must_include_patterns:
- "\[chunk_"
forbid_patterns:
- "guaranteed SLA"
judge_profile: tempered_3
Practice
Practice Attach rollback steps if cost-per-request crosses your guardrail. — 56 Bump 19.