All 127 posts in date order, newest first. ← back to topics
Request → N-eyes approve → window-of-time → automatic expiry, with every transition written to a hash-chained audit log. The package that closes Gap #1 from the PCSE map.
How a 200-line Go handler turns an audit log and an eval store into a regulator-friendly answer to "why did the AI decide that?" — without leaking a single byte of PHI.
Google's GKE AI infrastructure docs list ~40 integrations. Here's a field map of which ones actually matter when the workload is a HIPAA-aware multi-agent medical AI, and where the gaps sit.
Mapping the IAPP AIGP body of knowledge to an open-source Go codebase you can actually read and run.
FHIR gets the press; HL7 v2 still moves the messages. A field report from building a real integration.
What goes in a HIPAA audit log, what stays out, and how to verify nobody tampered with it.
What you fall back to when the model fails is the contract you actually offered the user. Reliability patterns from a clinical-AI production deployment.
Microsoft's Multi-Agent Reference Architecture, rendered as five Go interfaces. Field notes from an open-source implementation.
Row-Level Security at the database layer, paired with HIPAA access controls at the application layer. A working implementation in Go.
What information-blocking rules look like when you have to enforce them in production code.