Finance: Expense Audit Review with Claude Code: Result JSON Schema

A production playbook for expense audit review in finance operations using Claude Code: result json schema, run-scoped inputs, logs, typed results, and artifacts.

Audience: Finance teams auditing employee expenses

The problem

Finance teams auditing employee expenses need expense audit review to run repeatedly against receipts, policy docs, card transactions, and reimbursement requests. In finance operations, the pain is not one good answer; it is repeatability, auditability, exception handling, and evidence that survives handoff.

Implementation path

Define the outer result contract once, let the expense audit review skill own body.data, and reject terminal output that does not match the expected schema.

Tradeoffs and failure modes

Schema enforcement adds upfront design work, but removes prompt parsing from the product surface. For expense audit review, the practical test is whether a second run can be debugged, retried, and consumed by a product without reading the raw agent transcript.

Result shape

{
  "schema_version": "argo.result.v1",
  "summary": "expense audit review completed",
  "body": { "type": "finance_expense_audit", "data": {}, "exceptions": [] },
  "artifacts": []
}

Run this on Argo