Case Studies How We Work Blog About Book a call
AI Services & Outsourcing · LegalTech · US

AI tool for insurance legal opinion drafting

Attorneys once read hundreds of pages of handwritten medical and police reports per insurance case. We built a multi-assistant LLM pipeline with topic-specific prompts, human review and structured output — at about $3–4 in OpenAI cost per case set.

Service

AI Services & Outsourcing

Industry

LegalTech · US

Team

Frontend · Backend · AI engineer

Technologies

Vue.js · FastAPI · LangChain · Python · Docker · OpenAI API

Client context

Brandon J. Broderick, a US personal-injury law firm, prepares legal opinions for insurance compensation from large, heterogeneous document bundles — often ~250 PDF pages of medical records, police reports and notes per case.

Challenge

Single-shot ChatGPT could not handle volume or topic separation. Assistants sometimes refused corrections; prompts needed iterative refinement; output had to match firm templates and highlight key conclusions in bold.

What we did

  • Split work across five specialised assistants, each with examples, decision templates and edge-case instructions.
  • Designed per-topic queries instead of one monolithic prompt; added session reset via API when an assistant stuck.
  • Built Vue.js UI and FastAPI backend with LangChain; containerised with Docker Compose.
  • Structured responses with bold highlights so attorneys verify and supplement quickly.

Process

  1. Proof that single-prompt approach fails on real 250-page bundles.
  2. Assistant design and prompt iteration against attorney gold samples.
  3. Format constraints and reload strategy for stubborn model turns.
  4. Production rollout with cost tracking (~$3–4 USD per case bundle).

Result and impact

Structured legal opinions generated in minutes instead of hours of linear reading; attorney throughput improved ~1.5× with AI handling first-pass synthesis.

1.5× faster attorney workflow
The AI highlights what matters — we focus on judgement, not page flipping.Managing partner (paraphrased from case materials)