Finance: Accounts Payable Close Review with Claude Code: API Runtime Pattern
A production playbook for accounts payable close review in finance operations using Claude Code: api runtime pattern, run-scoped inputs, logs, typed results, and artifacts.
Audience: Finance operations teams closing AP
The problem
Finance operations teams closing AP need accounts payable close review to run repeatedly against invoices, approvals, purchase orders, payment runs, and exception reports. In finance operations, the pain is not one good answer; it is repeatability, auditability, exception handling, and evidence that survives handoff.
Implementation path
Package the accounts payable close review instructions as a skill, send invoices, approvals, purchase orders, payment runs, and exception reports 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 accounts payable close 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=finance-ap-close
inputs[]=@./input-pack.zip
result_schema=argo.result.v1
Run this on Argo