Narrative flow profile
Document routing
Non-generative classification pipeline for routing documents.
Abstract pattern
Non-generative classification pipeline
Shows that the same governance model works for a small classifier, with live gating, monitoring, and evidence-backed promotion.
- Manual Instrumented boundary; human performs the governed effect.
- HITL Automation proposes or prepares the effect and a human authorizes it before execution.
- HOTL The effect executes with asynchronous human oversight.
- Autonomous The effect executes under declared evaluator and demotion policy.
Narrative task profile
Document routing
Shows that the same governance model works for a small classifier, with live gating, monitoring, and evidence-backed promotion.
- Boundary
- Input is the document plus metadata. Output is a label and a routing destination.
- Evidence log
- Document features, predicted label, evaluator verdict, downstream correction when a human reroutes the item, and the handling outcome.
- Evaluator
-
- Property
- routing_decision_validity
- Target
- Input and output
- Technique
- Schema validation, out-of-distribution detection, and low-confidence escalation in flight, with downstream reroute monitoring behind the scenes.
- Evaluation basis
- invariant: routing_schema_and_out_of_distribution_invariants
- Epistemic status
- ground_truth
- Version
- 1
- Authority
- blocking
- Placement notes
-
- autonomous
- monitoring, in-distribution high-confidence decisions route directly; live reroute rate and drift monitors run continuously
- hitl
- blocking, out-of-distribution and low-confidence documents are held for human triage
- Promotion rule
- Held-out precision and recall meet the bar and live reroute rate stays low, so the pipeline can route directly.
- Demotion
-
- Rule
- Reroute rate climbs above threshold or a drift monitor fires, expanding the escalation scope and returning uncertain documents to human handling.
- Fallback
- Out-of-distribution and low-confidence documents route to human handling as a permanent design constraint.
Teaching point
What this flow proves
The live evaluator and the promotion evidence are different things, and both are required if the automation is going to stay safe.
Teaching context
Why this flow is governed this way
- Worker context
- A routing classifier with no generative model in the loop.
- Without PAA
- Routing errors surface only as downstream complaints; there is no live signal for drift or confidence degradation; a bad batch ships in full before anyone knows.
- Never full-auto
- Out-of-distribution documents, the classifier declares uncertainty on these and routes them to human handling as a permanent design constraint, not a temporary state.
This page is linked from the canonical card set on the flows index.