Lesson 140: Human-in-loop handoffs
Focus
Document interfaces between humans, retrieval, and policy engines. Token Human-in-loop handoffs:140 keeps neighbouring lessons differentiable.
Key ideas
- Thread: Human-in-loop handoffs · drill v10 · spin
372446. - 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
Retrieval partitioning plan
| Slice | Tokens | Retrieval mode | Notes |
|-------|--------|----------------|-------|
| FAQs | 521 | hybrid@0.57 | keep tables contiguous |
| Policies | 563 | dense@0.73 | include footnotes |
Drill: justify why chunk boundaries fall where they do for lesson 140.
Practice
Practice Simulate degraded retrieval once; screenshot graceful degradation copy. — 140 Bump literals mindset by 17.