Insights
Practical writing on AI systems engineering, security as a design choice, and the difference between a demo and a system you can trust in production.
July 13, 2026
What it takes to analyze contracts, clinical records, and regulatory documents with AI when the output has to survive audit — extraction vs. understanding, RAG architecture, hallucination control, and the decisions most teams discover too late.
June 19, 2026
If you're a healthcare CIO or VP Engineering deciding whether to buy a clinical-AI vendor or build, this is the decision framework we walk clients through. We've engaged on both sides — built systems for clients who decided to build, helped buyers evaluate vendors for clients who decided to buy. The choice is not alway
May 29, 2026
If you're building clinical document AI and your data source is an EHR, you'll touch FHIR. The question is not whether — it's how to make FHIR resources useful as both retrieval input and structured output for a RAG system. This post covers the patterns we ship in production.
May 22, 2026
The companion to our [audit-ready-ai-five-questions](/blog/audit-ready-ai-five-questions) post — that one tells you what an auditor will ask. This one tells you how to build the system that answers them. Code samples in TypeScript, deployment patterns for AWS, and the schema we ship to clients.
May 15, 2026
A reference architecture for the clinical-document AI system you wish your last vendor had built. Diagrams, BAA-eligible vendor stack, HIPAA control mapping, and the cost model — written by engineers who have shipped this in production at a specialty pharmacy and a clinical-ops platform. If your team has a 90-day deadl
May 4, 2026
AI procurement in healthcare is harder than software procurement was a decade ago. The data path is more complex, the regulatory exposure is broader, and the vendor ecosystem includes everything from established health IT firms to two-person startups with a Cohere wrapper.
May 2, 2026
Both platforms work for regulated workloads. Both offer BAAs. Both run inside your covered cloud tenancy. Both have audit logging that meets HIPAA's technical safeguards.
April 30, 2026
RAG systems have a reputation for being cheap to prototype and surprisingly expensive in production. The reputation is half-right. Production RAG is not expensive because of any single line item; it is expensive because the cost components compound across volume in ways that are not obvious until you look at the bill.
April 29, 2026
For almost any compliance-bound AI workload, the answer is RAG. We say this not because RAG is fashionable, but because the data lifecycle obligations in regulated industries push you toward keeping data out of the model.
April 26, 2026
Most legal document automation projects we see start with the same question: "Should we buy HotDocs / Contract Express / Documate / Gavel, or build something?" The answer depends on what you are actually trying to automate.
April 22, 2026
The framing of "build vs. buy" does not capture this choice well. ChatGPT Enterprise and Microsoft Copilot are managed assistants — productivity tools for individual users. A custom AI system is an application: scoped to a specific workflow, integrated with your data, deployed inside your tenancy. They are different ca
April 18, 2026
If your AI agent operates in a regulated environment — healthcare, legal, financial services — the audit log is not a feature. It is the artifact you produce, after the fact, to answer the questions that an auditor or breach investigator will ask.
April 15, 2026
When you build a RAG system that touches PHI, the vector database is in the data path. That means it has to be on your BAA, encrypted at rest with controls you can demonstrate, isolated by tenant, and capable of producing audit logs that are useful to a Security Officer.
April 9, 2026
In financial services, the AI pilots that ship are not the most technically impressive ones. They are the ones whose teams understood, before they started, what production deployment actually requires.
April 2, 2026
"We support HIPAA" is a sentence vendors say. What it means in practice ranges from "we have a BAA template ready to send" to "we have never seen a healthcare customer and we hope it works out."
March 21, 2026
Every AI system in production will eventually produce an output that someone wants to investigate. A patient will ask why a recommendation was made. A regulator will ask what data was used. An auditor will ask whether the system has been operated within policy. A breach investigator will ask what data the model saw dur
February 17, 2026
Tampa Bay's technology ecosystem has changed materially in the past five years. The pandemic-driven relocation wave that began in 2020 brought a mix of remote workers, founders, and enterprise teams who chose Tampa for reasons that are now structural advantages: no state income tax, lower cost of living relative to coa