DocuLens AI
400 pages. One clause. Under three seconds.
A UCITS prospectus runs to 400 pages. A private equity memorandum can exceed 600. DocuLens finds the specific clause you need, returns the value, the section heading, the page number, and the verbatim passage it came from — so a human can verify it in ten seconds rather than trusting a model.
Prospectuses · KIID/KID · Offering memoranda · Loan agreements · Compliance filings
Transferable securities in the form of equity and debt instruments listed on Regulated Markets within the EEA, as defined under Article 50(1)(a) of the UCITS Directive.
Part III — Investment Restrictions, Clause 3.1(a)
Page 87 · Confidence 0.97
Compliance officers and fund analysts read documents of extraordinary length to find single clauses. Pure vector search paraphrases well but misses exact regulatory terminology. Pure keyword search finds defined terms but misses anything phrased differently. Neither is good enough alone when the answer feeds a regulatory filing.
| Challenge | How DocuLens handles it |
|---|---|
| 400-page document, need one clause | Pinpoints the exact page and paragraph in under three seconds |
| Inconsistent terminology across documents | Semantic embeddings bridge synonyms and variant phrasing automatically |
| Tables and structured data inside PDFs | Table-aware chunking preserves rows, columns and nested headers |
| Cross-document queries | Entity resolution links related sections and defined terms across files |
| Ambiguous regulatory language | Opus 5 interprets context and qualifies the extracted value rather than flattening it |
BM25 gives high recall on technical terms and defined phrases. Dense vector search catches paraphrase and concept. Reciprocal Rank Fusion merges both into one relevance ranking — which is why hybrid beats either method used alone.
Layout-preserving parse
PDF parsing that maintains reading order, column flow, headers, footers and page numbers — so a returned page number actually corresponds to the printed document a reviewer is holding.
Semantic chunk boundaries
Haiku 4.5 identifies natural section breaks — clauses, definitions, schedules — instead of splitting at a fixed token count that cuts a definition in half.
Table serialisation
Tabular data is detected and serialised into structured JSON before chunking, so a fee schedule stays a fee schedule rather than becoming a run of disconnected numbers.
Dual index
Every chunk is written to both a dense vector index and a BM25 inverted index, and tagged with page number, section heading, chapter, entity types and document date.
Every response is auditable. In a regulated workflow, an answer without a source is not an answer.
| Stage | Model | Why this one |
|---|---|---|
| Semantic chunk boundary detection | Haiku 4.5 | Thousands of classifications per document during ingestion — speed and cost dominate here |
| Query intent and entity type | Haiku 4.5 | Classifies the query as definition lookup, value extraction, table query or cross-reference |
| Answer synthesis and extraction | Opus 5 | Dense legal and financial language needs the strongest reasoning available — this is where accuracy is won |
| Cross-document entity resolution | Opus 5 | Linking defined terms and cross-references across multi-hundred-page documents is genuinely hard |
| Confidence scoring and flagging | Sonnet 5 | Evaluates extraction quality against source text and surfaces borderline cases for review |
Figures from our own benchmark set. We'll walk you through the method — and where the numbers are weakest — on a call.
Designed for a workflow where a wrong answer is a filing error.
DocuLens was built by our own engineering team for financial and legal institutions, where the cost of a confidently wrong extraction is not a bad user experience — it is a compliance failure.
That constraint shaped every design decision: hybrid retrieval instead of vector-only, verbatim source excerpts on every response, and an automatic human-review flag below a confidence threshold. The system is built to be checked, not trusted.
Work with the team that built it →Test it on a document you already know
Pick a prospectus your team has reviewed manually. Book a call and we'll run DocuLens against it — the useful test is whether it finds what you already found.