Live system · MediGovern RAG
Governed AI for healthcare prior authorization.
A data-governed RAG pipeline that ingests policy PDFs, benefit tables and FHIR records, runs every document through a six-rule data-quality gate before embedding, and answers coverage questions with grounded citations, confidence scoring and a deliberate ABSTAIN path. Built around CMS-0057-F. All data is 100% synthetic — no PHI.
Open the governance dashboard inside this page.
The live MediGovern dashboard — what the system knows, what it has quarantined and why — loads in a window over this page. Backed by a FastAPI service with Anthropic Claude and a pgvector knowledge base.
Why it matters
Governed AI, built for a regulator's question.
I build governed RAG, not "chat with a PDF". The governance layer lives underneath generation: a DQ gate before embedding, confidence computed from evidence, an explicit ABSTAIN on conflict, and full lineage on every query, chunk and answer.
CMS-0057-F requires health plans to answer prior-authorization requests within 7 business days (2026) and urgent ones within 72 hours (2027), exposed over FHIR. This operationalises that obligation — and when a regulator asks "how did you decide?", the answer is already logged.
Governance controls
Pipeline
Ingest
Typed loaders for PDFs, CSV benefits and FHIR bundles — traceable to source.
Metadata
Extract type, IDs, dates, CPT/ICD, payer and plan.
DQ gate
Six rule families: pass, warn or quarantine — before embedding.
Embed
Chunk + bge-small embeddings into pgvector with a metadata index.
Retrieve
Metadata pre-filter, then semantic search grounded in policy text.
Answer
Cited answer + computed confidence, or ABSTAIN on conflict.
Audit
Immutable lineage record + audit packet for every query.
Built with
A free, reproducible stack.
Explore everything