customer_support · finance · workflow
Ramp builds AI Tour Guide agent to help users navigate its financial operations platform
Ramp's platform has many layers of functionality and users face an onboarding curve, requiring time to become platform experts. Ramp wanted users to self-serve faster without calling customer support.
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 · Classifier routes query
A classifier intelligently identifies relevant queries and automatically routes them to the Tour Guide feature when appropriate.
Tools used
LangChainLangSmithLangGraph
Outcome
Tour Guide increases user productivity and platform accessibility while building user trust through step-by-step transparency. Letter-labeling of UI elements in the prompt led to a significant improvement in output accuracy.
What failed first
An initial multi-step agent making two separate LLM calls — one for planning and one for grounding — was accurate but too slow for an acceptable user experience. Context stuffing with user screenshots was also found to be less effective than focused, well-enriched interactions.
Results
Volumesignificant improvement in output accuracy
Grounding & classification
Source type: platform led case
22 fields verified against source quotes.
agentic workflowai agentcomputer visionform submissionfailure mode describedhuman review describedmetric backednamed customertools describedworkflow describedfinancial servicessoftwareaccuracy improvementemployee productivityplatform led caseback office opscustomer supportagentic task execution