About · who's behind it

Led by a doctor who builds real, working AI.

LevaIQ is led by Dr. Jean-Paul Leva — a practicing physician who builds real, working AI at the speed of a whole tech team. It started with a wall of post-it notes and a year of waiting on vendors who never delivered. Today his whole practice runs on systems built in-house and owned outright — and this page is the story of how, told in his own words and his own messages.

Dr. Jean-Paul Leva, physician and founder of LevaIQ
How LevaIQ is different

Built in-house, at team scale.

Most businesses buy AI as a black box from an agency or a software vendor and rent it forever. LevaIQ takes the opposite approach: the systems are built in-house, and you own them — the patient-facing agents, the links into the records system and the other software, the day-to-day automation — with today's best AI doing the work of a whole tech team. We learned why this matters the hard way: over a year paying vendors and waiting, then bringing the build in-house and finishing it 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, every piece of work reviewed like a tough critic would, and everything checked against the real source instead of taking the AI's word for it. That discipline is what lets LevaIQ build like a much bigger team — and it's what we bring to a business that wants to actually own its AI.

The origin

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

Every firm has a founding story. Ours is documented. What follows is in Jean-Paul's own words — the actual sequence, from his own messages, that ended with the system being built in-house.

Before
It started with post-it notes.
The office ran on post-it notes and memory. I replaced them with a serious system for tracking patients and leads — and then watched it sit barely used. That taught me the lesson underneath everything here: software is only as good as the people who have time to run it. What I actually needed wasn't another program. It was a worker — one who never takes a vacation, never makes the same mistake twice, and actually does the work.
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 the build moved in-house.
Months in, I spelled out the real problem: we're too slow to answer texts, and an AI agent could fix it. The in-house build had already started. 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 in-house SMS agent went live — confirming real patient consults in English and Spanish.
Feb 16, 2026
Everything else followed.
Two days later the project that became all of this began. The agency never built it. LevaIQ did — and now other practices can 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 [our build tool]."
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
Excerpt: "we don't have lot's of works to do now…" [sic]
How we 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 same ones we set up inside every business we work with. Every build follows the same method:

Check everything against the real source

The AI's work gets checked against the real records, the real history, 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

Guardrails are built in so the AI literally can't slip a private note — 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 comes with an off switch and starts turned off. Nothing turned on is permanent, so we can move fast without betting your business on it.

Nothing is tribal knowledge

Every automation is built from a saved, written recipe — not hand-tinkered in a control panel. Anything can be rebuilt and double-checked at any time, which is how dozens of them run safely, day and night, no matter who's in the room.

“I didn’t wait for someone to build me the future. I built it. If you’re tired of waiting too — that’s exactly where we start.”

DR. JEAN-PAUL LEVA · FOUNDER, LEVAIQ

Work with LevaIQ

Want your business to run on AI you own?

We help medical and aesthetic practices — and any business that runs like one — set up the same kind of systems you see in the work: built for you, owned by you, not rented from a vendor.