Lesson 057: Eval harness hardening
Focus
Bias toward observable metrics: latency, cost, escalation rate. Token Eval harness hardening:57 keeps neighbouring lessons differentiable.
Key ideas
- Thread: Eval harness hardening · drill v7 · spin
18937. - 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-9866
route: support_rag_v7
must_include_patterns:
- "\[chunk_"
forbid_patterns:
- "guaranteed SLA"
judge_profile: tempered_3
Practice
Practice List five adversarial prompts using your org's domain nouns. — 57 Bump 23.