Logistics: Freight Exception Review with Claude Code: API Runtime Pattern
A production playbook for freight exception review in logistics operations using Claude Code: api runtime pattern, run-scoped inputs, logs, typed results, and artifacts.
Audience: Logistics operations teams
The problem
Logistics operations teams need freight exception review to run repeatedly against tracking events, bills of lading, invoices, carrier notes, and exception policies. In logistics operations, the pain is not one good answer; it is repeatability, auditability, exception handling, and evidence that survives handoff.
Implementation path
Package the freight exception review instructions as a skill, send tracking events, bills of lading, invoices, carrier notes, and exception policies as run-scoped inputs, execute with Claude Code, poll terminal status, and consume argo.result.v1 instead of parsing a transcript.
Tradeoffs and failure modes
The API boundary forces the workflow to define inputs, terminal states, and result shape before customers depend on it. For freight exception review, the practical test is whether a second run can be debugged, retried, and consumed by a product without reading the raw agent transcript.
Run request
POST /api/skills/<skill_id>/run
provider=claude-code
workflow=logistics-freight-exception-review
inputs[]=@./input-pack.zip
result_schema=argo.result.v1
Run this on Argo