Logistics: Bill Of Lading Audit with Claude Code: API Runtime Pattern
A production playbook for bill of lading audit in logistics operations using Claude Code: api runtime pattern, run-scoped inputs, logs, typed results, and artifacts.
Audience: Freight audit teams
The problem
Freight audit teams need bill of lading audit to run repeatedly against BOLs, shipment records, carrier invoices, accessorial charges, and rate cards. 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 bill of lading audit instructions as a skill, send BOLs, shipment records, carrier invoices, accessorial charges, and rate cards 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 bill of lading audit, 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-bol-audit
inputs[]=@./input-pack.zip
result_schema=argo.result.v1
Run this on Argo