Platforms & People
Book a callCustom development
Legal · RAG & document intelligence · India

Clause search across two decades of contracts, with every answer cited

Permission-aware retrieval over 200,000 contracts and opinions, answering at clause level with a citation on every line.

Confidential — corporate law firm
RAGDocument intelligence
⌕ limitation of liability capped at 12 months' fees, SaaS

“…the aggregate liability of the Supplier shall not exceed the fees paid in the twelve (12) months preceding the claim…”

MSA-2019-044 · §12.3 · p.14

2 more precedents · matter access verified
3 citationsrefuses without a source

200k docs

searchable at clause level

every answer

carries a clause-level citation

matter-scoped

access enforced at retrieval time

The problem

Associates spent hours finding precedent clauses across roughly 200,000 contracts and opinions held in three document systems — and could not rely on a general chatbot without re-verifying every line.

What we built

  • Ingestion across three document systems with OCR, clause-level chunking and matter metadata
  • Hybrid retrieval and reranking tuned on real questions from the firm's own associates
  • Answers that cite the exact clause, refuse when support is missing and respect matter-level access rights
  • Deployed in the firm's own cloud tenancy, with no client data used for model training

Stack

Azure OpenAICohere RerankpgvectorPythonAzure

Want something like this?

Tell us what you are building. A senior engineer replies within one working day.

Custom development