finance_ops · finance · workflow
How Ramp built a policy agent that handles more than 65% of expense approvals autonomously
Expense approvals were a tedious manual responsibility for managers and finance teams, and applying LLMs to a finance product required careful design to avoid losing user trust through low-quality or unexpected outputs.
How it works
Common implementation structure
How this type of workflow is generally built, generalized across documented cases — not tied to any one vendor's stack. Click any stage to read what happens there. Specific products that implement these stages appear in “Tools commonly seen” below.
Stage 1 · Expense submitted for approval
Expense approval, traditionally a manager's responsibility, is now routed to a policy agent that finance teams can trust to match or exceed human judgment.
Tools used
workflow builder
Outcome
Since enabling the policy agent at Ramp, more than 65% of expense approvals are fully handled by the agent, and a feedback loop continuously reduces human workload while improving policy accuracy.
Results
Volumemore than 65%
Grounding & classification
Source type: technical build writeup
23 fields verified against source quotes.
agent assistagentic workflowai agentpolicy documentreceiptfailure mode describedhuman review describedmetric backednamed customerproduction runtime claimedtools describedworkflow describedfinancial servicessoftwareautomation rateemployee productivitytechnical build writeupback office opsfinance opsai draft human approvalautonomous resolutionescalation workflow