Finance: Accounts Payable Close Review with Claude Code: Sandbox Policy
A production playbook for accounts payable close review in finance operations using Claude Code: sandbox policy, 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
Run accounts payable close review in an ephemeral sandbox, keep provider credentials in the broker, expose narrow tools, and store logs outside the workspace for review.
Tradeoffs and failure modes
A narrower runtime blocks ambient machine behavior, but it gives security reviewers a concrete boundary. 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.
Runtime boundary
filesystem: /skill and /skill/.argo/inputs only
network: deny by default
artifacts: /skill/output/artifacts
logs: retained outside sandbox
provider: Claude Code
Run this on Argo