Skip to content
← All demos
001PreviewBanking, Finance, FinTech & Insurance

Agentic Claims Intake & Triage

Upload a claim, watch the agent extract entities, run a grounded coverage lookup, cross-check for fraud, and escalate to a human when confidence drops.

What it does

A claim arrives as a document. Normally an adjuster reads it, keys the details into the claims system, checks coverage by hand, and decides where it goes.

This pipeline runs those steps as one flow: n8n parses the document, an LLM extracts entities against a fixed schema, a grounded lookup checks coverage, and a fraud cross-check scores the claim.

When the confidence score drops below threshold, the claim escalates to a human instead of auto-deciding. Every step writes to an audit trail, so any routing decision traces back to the evidence that produced it.

Architecture

How it's wired

  1. 01Presentation
    Next.js on Vercel

    Claim upload, live status, and rendered payload for the demo.

  2. 02Orchestration
    n8n (cloud-hosted)

    Document parsing, coverage lookup, fraud cross-check, and the human-in-the-loop escalation gate.

  3. 03Data
    TODOObject storage + routing queues

    Claim documents, extraction records, routing queues, and the audit log.

  4. 04AI
    OpenAI API (schema-validated calls)

    Entity extraction, grounded coverage lookup, and fraud scoring.

End-to-end flow

Claim uploaded on the demo page → n8n webhook receives the file reference → document parsed and entities extracted against a fixed schema → grounded coverage lookup runs → fraud cross-check scores the claim → confidence below threshold escalates to a human, otherwise routes to the correct queue → audit record written, structured result returned.

Sample payload

What goes in, what comes out

Mock data — representative of the production schema.

Input
{
  "event": "claim.received",
  "submitted_at": "2026-07-05T14:12:00Z",
  "source": "claims.elwoodberry.com",
  "fields": {
    "filename": "auto-claim-4471.pdf",
    "pages": 12,
    "policy_ref": "MOCK-2026-0091"
  }
}
Output
{
  "status": "triaged",
  "confidence": 0.91,
  "routed_to": "queue:adjuster-review",
  "audit_id": "ias-demo-001-0001"
}

Want this for your team?

Tell me the workflow. I'll show you what it looks like built.

Book a call