Data engineering · Analytics · Applied AI
Practical, privacy-first AI and data systems.
This is where I write up the projects I build: retrieval-augmented systems, local LLMs, and the data pipelines that feed them. Real systems, documented end to end, not slideware.
Latest writing
All posts →
Overwatch: The Real-Time Data Layer Jackson Health Already Owned
A first-person look at Overwatch, the in-house real-time alerting platform built at Jackson Health System: three use cases, ascending stakes, and the line that explains why most organizations never build one.
The Fragmentation Tax: Why Your Field-Service Stack Keeps Costing You Money You Can't See
No-shows, missed calls, and lost leads in field-service businesses aren't five separate problems. They're one problem, no owned data store, wearing five different masks.
The Accidental Manager
Computerization made everyone an accidental secretary. AI is making everyone an accidental manager, and the durable edge is knowing where mistakes come from in your business, not knowing the tools.
We Built a Neural Reranker and Then Threw It Away
A cross-encoder reranker is the standard next step for a RAG pipeline. We evaluated one on a real retrieval product, it confidently ranked the wrong documents first, and the replacement was a scoring function you can read in one screen.
The Belief Gap vs. the Readiness Gap in Healthcare AI
97% of health leaders believe AI is essential. Almost none feel ready to deploy it. The reason lives in fragmented EHR data, not budget or appetite, and having a FHIR endpoint doesn't mean that's solved.
The Minimum Viable RAG: What a Small Team Actually Needs
The four-part RAG pipeline in plain language: why the compute is cheap and CPU-bound, why document preparation is the hard part, and why owning your data layer beats owning the model.
Healthcare demo projects
Real, working systems, not slideware. Each one is documented end to end: the problem, the build, and what it actually does.
