I have been cutting code and design since I was sixteen. Two decades later the discipline hasn't changed: no framework where one line will do, no ornament that isn't structural, nothing shipped that I wouldn't sign. Not a generalist who also does AI — that discipline is now spent on the specific, deep, expensive problems: inference cost curves, the reliability of systems that decide, the architecture that has to hold under real load.
I work the way a jeweller works — slowly, on one piece at a time, until the thing is exact. Futurist nerve, Benedictine patience. Ora et Labora: pray and work, then work some more.
What you get is not a template with your name on it. It is a piece made to your measure, finished to the last facet — and quiet enough that only the eye that knows how to look will see how much is inside.
You don't buy hours. You buy a finished piece: infrastructure that holds, data that stays correct, intelligence that costs what it should — and a surface calm enough to conceal the work that holds it.
Intelligence joined to the data and tools you already run — it finds, sorts, routes, and decides — with faults handled the way any serious service handles them. Not a chatbot bolted onto a website.
Ready-made software fits nobody exactly — so we build the layer that is yours alone: your own data flows, work that decides and acts, and the quiet links between your tools, owned outright instead of rented from a vendor. This is the core of the practice — a system only you hold the keys to.
Fast, correct front ends wired to APIs and data models built to hold — not a static site with a form. What people touch is the surface of a system engineered underneath it.
The machinery beneath, the clocks that run the work, and the joins between the tools you already use — built to fail in plain sight, recover without fuss, and keep producing with no one standing over them.
Three houses, and this atelier. Each piece is shown because it carries a full cut — identity, system, and the discipline underneath — not because a portfolio needs filling.




In the trade, an assay certifies what a piece is actually made of. I offer exactly that for AI systems: fixed scope, fixed price, two weeks — where it breaks under load, what it truly costs per task, whether the architecture survives contact with production. Delivered as a signed written verdict, including the honest one: sometimes the verdict is that what you have is fine.
Every number in this house runs on hardware I own, and carries its date. The bench is open — step in →
Every act of AI runs on metered words — what a model reads and writes. You either rent that capacity as you go (a bill that grows with use) or own the machine (one fixed cost, however much you use it). Three numbers, honest answer — including "keep renting" when that's what the arithmetic says. Nothing you type leaves this page.
Reliability under real load, not demo conditions. True cost per task across your actual mix. Failure modes named before they're expensive. Architecture judged by someone who runs his own inference, not someone reselling someone else's. Scope and terms on enquiry — one assay at a time, like everything else here.