Methods note
From rule text to a checkable model
A worked example on SEC Rule 201: fields extracted by an LLM and tied to exact phrases, reviewed by a person, then checked against a stated property.
Home / Insights / Document and regulation intelligence
Research topic
Document and regulation intelligence
Rules, contracts and filings are written as prose, and the systems that depend on them run on fields: an obligation, a trigger, a threshold, an exception, a deadline. Document and regulation intelligence is the work of reading one into the other and keeping the link between them, so every field traces back to the words it came from.
Research on document and regulation intelligence
The research here covers how that work is measured and checked: how rule text becomes a checkable model, how extraction accuracy is scored field by field, what public benchmarks show about AI contract review and how an obligations register is read from regulation text.
Work with us on document and regulation intelligence
Rillor uses LLMs to turn rulebooks, regulatory filings, contracts, technical specifications and legal decisions into structured, source-linked records and machine-checkable models. Each field keeps a link to the exact phrase it came from, scanned pages are read with OCR, and a person reviews every record before it is used. When a source changes, the records that depend on the changed passage go back to review.
Notices
AI outputs can be wrong. Important decisions should include human review.
Bring us the documents you rely on.
Send a sample of the rulebooks, regulations, contracts or filings you work from and the fields you need from them.