Lesson 057: Evaluation harness depth
Focus
Document interfaces between humans, retrieval, and policy engines. Token Evaluation harness depth:57 keeps neighbouring lessons differentiable.
Key ideas
- Thread: Evaluation harness depth · drill v7 · spin
608522. - Habit: pair every model utterance with a trace_id you could paste into Grafana.
- Guardrail: write one RACI bullet referencing this lesson tomorrow.
Deep dive notebook
Synthetic drill artefacts
Eval YAML snippet
case_id: GX-9866
input_stub: summarise incident_ticket_pool_9
must_include_patterns:
- "\[chunk_"
forbid_patterns:
- "SLA 15m" # unless citations exist
judge_profile: tempered_4
Practice
Practice Simulate degraded retrieval once; screenshot graceful degradation copy. — 57 Bump literals mindset by 17.