Anyone can build you a demo that works.
Two afternoons and an API is enough to show something that answers well in front of a committee.
Production is another matter, and the AI is not what holds it up.
It is access permissions, deciding which version of each document is the right one, and data that cannot leave your network.
An AI system does not break: it keeps answering, only worse.
Which is why trying it for a while proves nothing. You measure it with a case suite that protects every change that comes after.
I build the whole product, with the AI inside.
Backend, admin panel, access control, payments, deployment and the test suite that protects it. If your case does not need AI, I say so before charging you for it.
Three things, and I do them.
I do not advise and leave: I build it and leave it running. No middle team, no reselling, on fixed-price projects or monthly dedication, with working pieces from the first week.
An assistant over your documents
It answers about your manuals, protocols, catalogues or internal policy, always citing the source. What stretches these projects is rarely the model.
See the service → 02AI that never leaves your building
Open models on your server or your GPU. No data travels to a third-party API, which is the only way to work with clinical records or legal files.
See the service → 03An audit of the AI you already have
Case suite, adversarial testing and a failure report with a fix plan. The suite stays yours and protects every future change.
See the service → 04The whole product, from zero to production
Backend, admin panel, accounts and permissions, two-factor, payments, deployment and the test suite that protects it. A medical SaaS with 84 doctors using it is exactly that, end to end.
See how it is built →This website is a working demo.
The assistant below is not a form in disguise. An open model answers it, running on my own GPU, with the same guardrails I build for a client: it invents no prices, admits what it does not know, and if it goes down it says so instead of breaking.
Answered by an open model hosted on my own GPU. No data travels to third-party APIs.
What could be built in your case?
Five questions and my own model tells you what it would build, where it would start and what it would not do. If your problem is not solved by AI, it says that too.
Two products built and running.
Where being wrong is expensive: health data and legal files, with human review and GDPR compliance.
A medical SaaS, built end to end
Co-founder and CTO. Reasoning engine with LLM and RAG self-hosted on a private GPU, a suite of nearly 300 clinical cases, 84 real users across 36 institutions.
- Co-founder and CTO
- Self-hosted RAG
- 300 regression cases
A law firm doing 70% less manual work
Drafts of civil claims with overnight processing. The lawyer always reviews and validates: the AI prepares, it does not sign.
- Civil law
- Human review, always
- Data stays inside the firm
Three steps.
Fixed-price projects or monthly dedication, always with reviewable deliveries.
-
01
An honest diagnosis
I look at your case and tell you what I would do, how long it would take and what the risks are. If you do not need AI to solve it, I tell you that too.
-
02
Building in deliveries
Working pieces from the first week, not promises. You see and validate every step on your own case.
-
03
Production and guarantees
Deployment, a test suite that protects every change, security and documentation so your team can maintain it.
Got an AI project on your hands?
Tell me what you want to build, or what isn't working. I'll reply with an honest assessment: what I would do, how long it would take, and whether you actually need AI to solve it.
Who I build with.
A company of my own and the teams I work with when a project needs more hands.
-
cofounder and CTO
Clinical decision support for orofacial pain, in production and in three languages. I build the reasoning engine, the infrastructure and the product.
-
partner
Custom software development with integrated AI. Web and mobile apps and digital platforms.
