About · the operator

A doctor who builds real, working AI.

I'm Dr. Jean-Paul Leva — a working doctor who builds real, working AI and ships it at the speed of a whole tech team, using today's best AI. I'd spent a year waiting on vendors to deliver the AI agent I wanted; when it didn't come, I built it in-house — live within days. In four months, my whole practice came to run on systems I build and own.

How I'm different

Built in-house, at team scale.

Most practices buy AI as a black box from an agency or a software vendor and rent it forever. I take the opposite approach: I build the systems in-house and own them — the patient-facing agents, the links into the records system and the other software, the day-to-day automation — using today's best AI as my tech team. I learned why this matters the hard way: I'd paid vendors for over a year to build my AI and waited, then built it myself in a fraction of the time.

The edge isn't the AI itself; everyone has that. It's the discipline: safety checks at every step, an off switch on every risky feature, I review my own work like a tough critic, and I check everything against the real source instead of taking the AI's word for it. That discipline is what lets a small operation ship like a much bigger one — and it's what I bring to a practice that wants to actually own its AI.

The origin

I asked them to build it. They didn't.

I did what every practice owner is told to do: hire the experts and wait. Here's the actual sequence — from my own messages — that ended with me building it myself.

Sep 2025
The first agent didn't work.
I'd hired vendors to bring AI into the practice. I shut one of their agents off — it was no good — and asked a simpler question: could we just build an AI that texts patients back and books them?
Dec 2025
I called it the year of AI agents.
I handed the agency a roadmap for 2026. At the very top: deploy AI agents for SMS and website chat. This was going to be the year.
Early Feb 2026
Still waiting — so I started myself.
Months in, I spelled out the real problem: we're too slow to answer texts, and an AI agent could fix it. I admitted I'd already started building it myself. The reply I got was, "Let me have a look."
Feb 12–13
"This is the dream."
I made the deck and wrote the build spec for the agent I wanted, and sent it over. That was the last thing I handed off.
Feb 14, 2026
I stopped waiting.
The SMS agent went live — confirming real patient consults in English and Spanish. I'd built it myself.
Feb 16, 2026
Everything else followed.
Two days later I started the project that became all of this. The agency never built it. I did — and now I help other practices skip the wait.
The receipts — from my own messages (names blurred)
Me → the agency · Dec 23, 2025 · 2026 roadmap
"Deploy AI agents for SMS and website chat."
Me → the agency · Feb 10, 2026
"It would be great if AI could be used like an agent to respond to texts and book consults. I've been playing with the idea of building this through Claude Code."
The agency · Feb 10, 2026
"We definitely need to create some AI agents for these kind of task. Let me have a look."
My SMS agent — live · Feb 14, 2026
"¡Perfecto, [paciente]! Su consulta con el Dr. Leva está confirmada."
The agency · Mar 16, 2026
"We don't have lot's of works to do now as you are doing most of the work your self."
How I build

The method is the edge.

Anyone can use today's best AI. Building safe systems that run every day comes down to a handful of habits — the ones I'd set up for any practice I work with.

Check everything against the real source

I check the AI's work against the real code, the history, and the live system — never just what it says. This very site was put through a tough review and fixed where it was wrong.

Guardrails, not hope

I build in guardrails so the AI literally can't slip its private notes — or a wrong date — into a patient's text. It's built to be right, not asked to be.

An off switch on everything

Every risky feature ships behind an off switch and a safe default. Nothing I turn on is permanent, so I can move fast without betting the practice on it.

Everything can be rebuilt

Every automation is built from a saved recipe, not hand-tinkered in a control panel. So it can always be rebuilt and double-checked — which is how dozens of them run safely, day and night.

Work with me

Want your practice to run on AI you own?

I help practices set up the same kind of systems you see in the work — built and owned by you, not rented from an agency.