Lesson 059: Eval harness hardening
Focus
Document interfaces between retrieval, prompts, and policy engines. Token Eval harness hardening:59 keeps neighbouring lessons differentiable.
Key ideas
- Thread: Eval harness hardening · drill v9 · spin
232397. - 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-10212
route: support_rag_v2
must_include_patterns:
- "\[chunk_"
forbid_patterns:
- "guaranteed SLA"
judge_profile: tempered_4
Practice
Practice Attach rollback steps if cost-per-request crosses your guardrail. — 59 Bump 17.