AGENT VIEW · how a machine reads this page. The dashed labels expose the semantic structure.
// Louis Rotellini · AI Product Engineer

I design and ship AI tools for concrete business use cases.

01 / Products

My AI products, from idea to production.

Five products built by piloting AI. The LLM is chosen per need: often Mistral for European compliance. Claude Code is how I drive development. Filter by stage, open a card.

02 / Live demo · eval gate

An eval gate, before production.

Describe an AI feature: a model judges it live against four hard, eliminatory rules. Every rule comes back with its reasoning, and with what you would need to add when it fails. My differentiator, reliability through rules, made playable.

Describe an AI feature
Eval gate: evals · human review · bounded cost · failure handling. Claude Haiku 4.5 judges each rule, the verdict is still computed server-side. The demo itself is capped: 6 runs, 600 characters.
Run the gate to see a live verdict.
03 / Machine experience

Built for humans, and machines.

In 2026, agents read your site as much as humans do. The same content, structured so an LLM can read it without guessing. Switch views.

profile.card
Louis Rotellini
AI Product Engineer · Full-Stack · Next.js · TypeScript · Node

Designs and ships AI products end to end: from scoping to model choice, evals, UX and production. I pilot AI; it doesn't pilot me.

next.jstypescriptllmragmistral
// application/ld+json
{
  "@type": "Person",
  "name": "Louis Rotellini",
  "jobTitle": "AI Product Engineer · Full-Stack · Next.js · TypeScript · Node",
  "skills": ["Next.js", "TypeScript", "LLM", "RAG"],
  "address": "Lille, FR",
  "products": 5,
  "shipped": 1, "prototype": 3, "scoping": 1
}

Generation can be delegated.
Judgment, never.

04 / Approach

Making a fallible system reliable.

An LLM-based system is probabilistic, therefore fallible. My job is to ship it to production anyway, without ever trusting it blindly.

A measurable target, not a feature

I never start from “add AI”, but from a target: a time to cut, a cost per task to cap, a success rate to hold. Business need first, model choice after. Often Mistral to stay in Europe, sometimes no AI at all if a rule is enough.

Drawing the deterministic / probabilistic boundary

The core move of the craft: deciding where a hard rule must apply and where the model may decide. DocTap has two pipelines. A 100% local mode where no data leaves the device, and an AI mode with OCR followed by human verification before export. I deliberately refused a named patient vault to stay out of the French HDS health-data scope.

Reliability comes from rules and evals

An LLM hedges by default; for a reproducible judgment I impose hard, eliminatory rules on it. That's the principle behind my scoring engine. This site's live demo makes it playable: an eval gate that scores a feature against those rules before production.

Directing AI, keeping the decision

I direct the implementation within strict limits: types, schemas, review. I don't re-read the code by hand: I run AI-assisted audits to flush out flaws, counter-audited by a second agent when the stakes warrant it. On a recent build, that caught an API route left exposed before production. Detection can be delegated; what ships to production is my call.

05 / Background

~10 years of web. I started in integration, then React / Next.js / TypeScript front-end. Now a Front-end Developer, I build products by piloting AI, from idea to production.

A real developer's path turned AI-augmented builder, not a no-code convert. That's what lets me direct AI instead of enduring it, and audit what it produces.

Clients · freelance work · front-end integration
DecathlonDamartIÉSEGBlancheportePromodCrédit MutuelDisneyland ParisLa Foir'FouilleTape à l'Œil
Louis Rotellini
06 / Contact

Let's build something.

Louis Rotellini · AI Product Engineer