Notes for engineers putting health data near a model: BAA scope, zero data retention, ePHI you forget you have, and the state laws that apply anyway.
Release bars for a nondeterministic product when you are the whole team.
Choosing a local extraction model by measuring two candidates on the same real pages.
How Everblue decides what it may say about AI and your data: on-device first, zero data retention as a flag, and a never-claim list.
Notes from Arbiter, a clinical-document RAG prototype on synthetic records: Safe Harbor, flattering recall metrics, and where Presidio's defaults miss.