All projects
InsuranceInsurer·2025

Claims triage copilot

RAG over policy documents with adjuster-in-the-loop approvals.

38% faster triage with cited answers clinicians and auditors trust.

Duration

11 weeks to production

Engagement

Discovery → production AI

Industry

Insurance

Client

Insurer

AI SolutionsCustom SoftwareData Analytics
Claims triage copilot — Insurer

−38%

Triage time

Median time to first decision

96%

Citation accuracy

On held-out evaluation set

11 wks

Time to production

Workshop to live desks

91%

Adjuster adoption

Weekly active among trained users

Project brief

What this project was really about

An insurer’s adjusters spent hours hunting policy clauses while claim queues grew. We shipped a private RAG assistant with citation-first UX, evaluation harnesses and human approval gates — production-ready in eleven weeks.

01 — Challenge

Adjusters lost time searching unstructured policy documents. Early AI pilots hallucinated clauses and could not survive compliance review.

  • Scattered PDFs and legacy claim notes
  • No evaluation suite for answer quality
  • Risk of uncited model recommendations
  • Need for full audit trails on every suggestion

02 — Solution

Private RAG over access-controlled corpora, an LLM gateway with logging, and a UI that refuses to recommend without a citation the adjuster can verify.

  • Ingestion pipeline with PII redaction
  • Vector store with row-level security
  • Eval harness wired into CI
  • Human-in-the-loop approval workflow
03 — Approach

How we delivered it

A phased programme with evidence at every gate.

  1. 01

    Corpus & risk workshop

    Defined refusal policies, citation requirements and which claim types were in scope for v1.

  2. 02

    Retrieval & evals

    Built ingestion, retrieval quality baselines and regression suites before expanding tool access.

  3. 03

    Copilot UI

    Adjuster workspace with cite-or-quiet behaviour and mandatory approval before claim action.

  4. 04

    Production hardening

    Latency budgets, cost controls, audit logs and a phased rollout across claim desks.

04 — Architecture

System shape

  • 01Document ingestion and chunking pipeline
  • 02Vector store with row-level security
  • 03LLM gateway with audit logs
  • 04Human approval workflow
  • 05Evaluation suite in CI
  • 06Observability for cost and latency

Deliverables

What shipped

  • Production claims copilot
  • Private document corpus with ACL
  • Evaluation harness and dashboards
  • Adjuster training and playbooks
  • Compliance review pack

Stack

PythonpgvectorLangGraphAzureReact

Client voice

Finally an AI tool our compliance team did not ask us to turn off.

James Okonkwo

Head of Claims Operations · Insurer

More work

Related projects

Have a programme that needs the same discipline?

Tell us about the constraints, the risk, and the outcome you need. We will respond with a clear engagement shape — not a slide deck of buzzwords.