kyc_aml · finance · workflow
Brex rebuilds customer onboarding as an AI-native multi-agent system
Brex's KYC and underwriting onboarding relied on manual judgment, implicit heuristics, and fragmented tools, creating a ceiling on velocity and scalability and causing onboarding to take days.
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 · Startup segmentation
Segmentation agents leverage data sources like LinkedIn via Clay, company website, and application information to determine whether a startup is professionally invested or likely to receive professional investment.
Tools used
ClayLinkedInOCR
Outcome
Brex's AI-native multi-agent onboarding now processes most eligible businesses in minutes, with card application auto-approval growing from 0% to 40%, an 85% reduction in business address RFIs, and a 70% reduction in manual identity reviews.
Results
Time savedonce took multiple analysts and several days now happens in minutes
Volume70%
Grounding & classification
Source type: technical build writeup
37 fields verified against source quotes, 1 dropped as unverifiable.
agentic workflowanomaly detectiondocument aidocument classificationfraud detectionmulti agent workflowocrbank statementcontractform submissionid documentbuilder submittedfailure mode describedhuman review describedmetric backednamed customerproduction runtime claimedtools describedworkflow describedbankingfinancial servicesautomation ratecycle time reductionemployee productivityerror reductionthroughput increasetechnical build writeupback office opskyc amlagentic task executionescalation workflowextract classify routehuman review queue