Clausebook
HIPAA redlining playbooks the lawyer owns.
- Ontologies & knowledge graphs
- NLP & information extraction
- Regulated & high-security environments
- Data science & evaluation
Build a Business Associate Agreement redlining playbook through an adaptive interview, then apply it to a real uploaded BAA. Clausebook splits the document into clauses, classifies each against an ontology and your playbook, and drafts redlines cited to HIPAA authority.
The problem
BAA negotiation is repetitive expert judgment that lives in one person’s head. Outsource it and you lose the positions you fought for. Keep it in-house and it does not scale past the person holding it.
The approach
Ownership, not automation. The playbook is the lawyer’s asset, the tool applies it, and every accepted edit writes back — so using the product is how the playbook improves. Clausebook is a software tool, not a law firm, and does not give legal advice.
How it works
- Ingest by paste or PDF, Word or text upload, extracted server-side
- Clause splitting, then classification against the Atlas ontology plus the tenant’s own playbook
- Redline drafting grounded in live citations from eCFR regulation text and CourtListener case law
- Accept or edit, with edits writing back to the playbook — the ownership loop
- Corpus mining that surfaces which of your past positions are well-evidenced and which are inconsistent
- Word export with native tracked changes
- Per-tenant isolation via row-level security
Stack
React 18 and Vite; a Python FastAPI backend alongside a serverless layer; Claude; Supabase Postgres, Auth and row-level security; Stripe.
Where it stands
- Roughly 118 test files, with CI, auth, row-level security and billing in place
- A typed legal-dependency graph that ranks concepts by importance rather than frequency, validated against held-out data