All case studies
Case study · AI/ML

RAG Knowledge Assistant for Insurance Ops

Built a Claude-powered RAG assistant over 12,000 policy documents — cut underwriter research time by 71% with full citations and a live cost dashboard.

Industry
AI/ML
Engagement
Discovery → Launch
Region
Global
Status
Live

RAG Knowledge Assistant for Insurance Ops · Cover image

01 · The challenge

What needed solving

Underwriters spent 40+ minutes per quote hunting through 12,000 policy PDFs, internal memos and case-law summaries — costing throughput and producing inconsistent decisions.

02 · Our approach

How we framed the work

We started with a discovery sprint to map the user journey, business goals and real constraints. From there we wrote a fixed-scope plan: clear milestones, weekly review gates on a staging URL, and a written exit criterion for every phase. The ai/ml space rewards teams that ship — not teams that plan — so we biased the engagement towards working software from week two onward.

03 · The solution

What we built

Built a hybrid-retrieval RAG pipeline (pgvector + BM25), Claude 4.6 Sonnet for reasoning, a LangGraph agent that asks clarifying questions, strict citation-only answers, and an internal eval harness with 240 golden questions. Live cost + latency dashboard for ops.

04 · The results

What changed for the client.

71%
Time Saved
94%
Eval Accuracy
< $0.08
Cost / Query
  • Underwriter research time dropped from 40 minutes to 11 minutes per quote

  • 94% answer accuracy on the golden eval set, every answer with source citations

  • Cost per query held under $0.08 via prompt caching and model cascading

Tech stack

ClaudeRAGpgvectorLangGraphFastAPIEval

Want a similar outcome for your business? We'd love to hear about it.

Your case study, next

Let's build the next one together.

Fixed-scope quote in 24 working hours.