How I build
The system behind the systems.
I work AI-native: agentic coding tools handle the heavy lifting while I set direction, review every change, and own the result. It's how a one-person practice ships production systems — fast, but grounded in tested code, clean data, and real workflows.
HOW I WORK WITH AI
An algorithm, not a vibe.
This is the loop I run.
Most data-science workflows stop at a notebook. Mine ships into production because every step has a gate — a spec, a test, a review, an observable system — and AI agents do the heavy work inside those gates.
- FRAME — WITH THE OPERATOR. Frame the problem with the operator, not the dataset.
- SPEC — DESIGN BEFORE CODE. Write the spec before any code.
- PLAN — REVIEWABLE UNITS. Decompose the spec into a reviewable plan.
- BUILD — TESTS WITH THE CODE. Build with agents — code and tests produced together, every step reviewable.
- VERIFY — MULTI-GATE. Verify against a stack of gates — types, lint, tests, eval/regression, secrets check, human review.
- SHIP — RELEASE-TAGGED. Ship with a release tag and a written rollback path.
- OBSERVE — LOGS & FEEDBACK. Observe in production — logs, traces, and incident feedback drive the next loop.
Three explicit gates: after SPEC the spec must be clear or work returns to SPEC; after VERIFY the multi-gate check must pass or work returns to PLAN; after OBSERVE production must be healthy or the next loop starts at FRAME.
The toolchain
Agents do the heavy lifting. I direct the work.
A stack of agentic coding tools, each pointed at what it does best. Tap any one to see what it is, where the field is heading, how it works — and where it shows up in my work.
The frontend
The interface layer. What you see and touch.
What renders in the browser — component-driven, typed end-to-end, and tuned for fast pages. Tap any tool to see what it is, where the field is, and where it shows up in my work.
The backend
Where the data lives. And how it gets out.
Typed APIs, real schemas, and the boring discipline that lets the front end stay simple. Tap any tool to see what it is, where the field is, and where it shows up in my work.
Let's build the next healthcare system.
I'm running a multi-site hospital equipment-tracking and analytics system in production, and I'm open to healthcare data, analytics, AI, and application engineering roles — remote, hybrid, or on-site. The best way in is a short conversation.
Start a conversation