expense_management · saas · workflow
How Ramp Built LLM-Backed Expense Policy Agents Users Can Trust
Expense approval was a tedious, time-consuming task traditionally handled by managers, and applying LLMs in 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
The policy agent is applied to the traditionally manager-handled task of approving expenses.
Tools used
LLMworkflow builder
Outcome
Since enabling the policy agent at Ramp, more than 65% of expense approvals are fully handled by the agent, with a feedback loop that reduces human workload and improves policy accuracy over time.
Results
Time savedreduces the amount of work humans need to do over time
Volumemore than 65%
Grounding & classification
Source type: technical build writeup
26 fields verified against source quotes.
agentic workflowai agentcontent generationpolicy documentreceipthuman review describedmetric backednamed customerproduction runtime claimedtools describedworkflow describedfinancial servicessoftwareaccuracy improvementautomation rateemployee productivitytechnical build writeupexpense managementfinance opsai draft human approvalautonomous resolutionescalation workflow