Jean-Paul Leva
drleva@drleva.com
A four-month build · Feb–Jun 2026

The year of
AI agents.

How one physician — told it would take an agency and a year — built the AI that now runs his practice. In four months. Alone, with a frontier model.

Scroll
Act I · The Setup

I’d built the practice
a brain.

An enormous CRM to run the office — roughly 800 properties, 381 workflows, ten pipelines. On paper, a machine.

But a machine is only as good as the people who run it.

365 of the fields I’d built were never touched. The system had outrun everyone in the building — and the work it was supposed to do simply wasn’t getting done.

Act II · The Ask

So I asked the experts
to build the agents.

I’d decided this was the year of AI agents. I’d already shut off one vendor’s agent — it was no good — and I handed the agency a roadmap with one thing at the top: deploy AI agents for SMS. Then I waited.

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 respond to texts and book consults. I’ve been playing with building this through Claude Code.”
Brightline Co. · the agency · Feb 10, 2026
“We definitely need to create some AI agents for these kind of task. Let me have a look.”
Act III · The Turn

They didn’t.
So I did.

I stopped waiting and built it myself, in Claude Code. On February 14, 2026, the SMS agent went live — booking real patients, in English and Spanish — two days before I’d even opened the repository that became all of this.

My SMS agent — live · Feb 14, 2026
“¡Perfecto, Daniela! Su consulta con el Dr. Leva está confirmada.”
Brightline Co. · 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.”
Act IV · What Followed

Then I didn’t stop.

Eleven systems, all live in my practice today — built between February 16 and June 16, 2026. Open any one for its own page →

01

Bilingual AI Patient Agent

Texts patients back any time — day or night, in English or Spanish — and books their appointments for them.

live since Feb 14
02

The Practice OS

The one app my whole office runs on — scheduling, patient records, billing, and the front desk, all in one place.

in daily use
03

The Automation Fleet

Around a hundred behind-the-scenes helpers that quietly handle the repetitive office work, around the clock.

always on
04

Google Ads Recovery

Our online ads had quietly stopped working. I found out why and rebuilt them so they bring patients in again.

recovered
05

Call Intelligence

Listens to every phone call and writes a clear summary into the patient’s file within minutes.

every call
06

The Connector

The wiring that links the AI to our medical-records system, so it can book real appointments — not just pretend to.

the plumbing
07

Clinical Scribe

Records a visit on an iPad and writes up the doctor’s note automatically, in English or Spanish.

on iPad
08

My Quality-Control Tools

The tools I built to double-check my own work, so the AI can move fast without making mistakes.

my edge
09

DealSnap

Snap a photo of a paper patient form and the right record is created for you in about thirty seconds.

from a photo
10

Lead Integrity

Makes sure “I reached the patient” really happened — it checks the phone and the calendar instead of taking someone’s word.

proof, not claims
11

ScribeSnap

A Mac app for the doctor: hold a key, talk, and your words turn into clean text anywhere on screen.

dictation
By the Numbers
0
live
systems
0
tracked
commits
0
production
workflows
0
days
solo + AI
0
person
building
How I Build

The model isn’t the edge.
The method is.

Anyone can call a frontier model. Shipping safe, production systems as one person comes down to a handful of disciplines — the ones I’d set up for any practice I work with.

01

Verify against primary sources

I fact-check the model against code, version history, and live systems — never the prose. This very site was put through an adversarial review and corrected where it was wrong.

02

Typed contracts over hope

Structure at every boundary, so a model physically can’t leak its reasoning — or a wrong date — into a patient’s text. Correctness is enforced, not requested.

03

Kill switches on everything

Every risky feature ships behind a flag and a safe default. Nothing I deploy is irreversible, so I can move fast without betting the practice on it.

04

The builder is the source of truth

Automations are generated from versioned scripts, not hand-edited. The system can always be rebuilt, diffed, and audited — which is how one person safely runs ~97 of them.

Work With Me

What I can build
for your practice.

I’m a practicing physician who runs my own practice and builds its AI myself — not an agency, and not rented software. Here’s how we could work together.

01

AI Roadmap

A clear, ranked plan of what AI can actually do for your practice — and exactly what to build first. A fixed-scope place to start.

02

Build one system

I build one of these into your practice, end to end — the patient texter, the scribe, call intelligence — live and working, not a demo.

03

Your whole Practice OS

The full build: the app your office runs on, the automations behind it, and the wiring that ties it together — owned by you.

04

Ongoing partner

I stay on as your fractional AI lead — building, watching, and improving the systems as your practice grows.

Everything is built in-house and owned by you — your data stays yours, every risky feature has an off-switch, and nothing is rented from an agency.

Book a 20-minute call →
Jean-Paul Leva · Leva Medical · Queens & Northport, NY
drleva@drleva.com