Banking & Fintech2025Confidential client

Representative engagement — details anonymised.

Due Diligence Engine

Due diligence is thousands of pages read under deadline pressure. We built a system that reads all of them, cross-references what it finds, and never cites a page it can’t show you.

Close-up of thin dark slate strata stacked like sheets of paper, one seam marked in orange
01

Challenge

An advisory team was spending the first two weeks of every engagement extracting the same facts from every data room: change-of-control clauses, indemnities, related-party transactions, covenant terms. Manual, repetitive, and error-prone at exactly the moment errors are most expensive.

Off-the-shelf AI tools summarised confidently and cited nothing. For work that ends up in front of a deal committee, an unverifiable answer is worse than no answer.

02

Approach

We treated hallucination as a structural problem, not a prompt problem. Every extraction runs through a typed pipeline: classify the document, segment it, extract against a schema, then verify each claim against the exact source span before it is allowed into the findings register.

Findings carry their evidence with them — page, paragraph, and confidence. Anything below threshold routes to a human review queue instead of the report.

The reviewing analyst stays in charge: the system drafts the findings register, the human signs it.

03

Outcome

First-pass document review that took two weeks now takes two days, and the partners trust it precisely because it refuses to answer what it cannot prove. The firm’s review capacity scaled without a single new hire.

30k+Pages per engagement
100%Findings with source citations
2wk → 2dFirst-pass review time
Built with
  • Claude
  • TypeScript
  • Postgres
  • pgvector
Services
  • AI Pipelines
  • Document Intelligence
  • Compliance
Next Project

Clinical Operations Platform

Healthcare2024