Expertise · Artificial intelligence

AI wired into your tools.In production, not in a demo.

Assistants that act inside your software, search across your documents, automatic reading of scanned files: I build AI for a specific job, in the cloud or entirely local.

MCP

MCP servers and clients that connect models to business tools

OCR + AI

Reading and information detection in an ERP for private clinics

100% local

AI that runs on the device or your server, with no external API

Build your AI project

Pick what you want AI to do for you: the diagram lights up the bricks to build. Tap a brick to see what it does.

1 · Your needs

Cloud or local?

Select your needs and I'll tell you which hosting fits best.

2 · What I build

01 Your data

02 Preparation

03 Intelligence

04 Use

Tap a brick

Each brick of the diagram is explained here. The dots mark what I have already put into production.

3 · Your brief

Select at least one need to prepare your brief.

Send this brief

Opens your email app with the brief filled in. Nothing is sent without you.

In the field

Missions carried out through IT consultancies and at software publishers, clients anonymized, plus the studio's own projects.

Current mission · AI development

Connecting AI models to business services

Building MCP servers and clients, and integrating with cloud AI services.

  • MCP
  • Amazon Bedrock
  • Anthropic API

Mission · Healthcare software publisher

ERP for private clinics

Python management software with AI modules: document OCR, automatic information detection and several other smart features.

  • Python
  • OCR
  • AI

Studio · OpenJEV Guard

AI embedded in the browser

An extension that hides content unsuitable for minors in real time, with AI running entirely on the device.

  • TypeScript
  • WebGPU / WASM
  • ONNX Runtime Web
  • Vision Transformer

Studio · Horrorpipe

100% local AI pipeline

Turns a topic into a narrated video: script, voice, shot generation, editing and subtitles, with no cloud API at all.

  • Python
  • Local LLM
  • ComfyUI
  • Kokoro TTS

Missions carried out through IT consultancies or at software publishers: clients anonymized. The studio's own projects are on the work section.

The toolkit

Proven technologies, chosen to last and easy to take over.

Models

  • Claude (Anthropic API)
  • Amazon Bedrock
  • Local LLMs
  • ONNX Runtime
  • Vision Transformer

Building blocks

  • MCP (servers and clients)
  • RAG
  • Agents
  • OCR
  • Information extraction

Languages

  • Python
  • TypeScript

Frequently asked questions

Another question? Write to me.

Does my data get sent to an AI provider?

Not necessarily. Depending on how sensitive it is, the model is called through a cloud service (Amazon Bedrock, Anthropic API) or runs locally, on your server or on the device. We settle this at the scoping stage.

What is an MCP server?

The Model Context Protocol is an open standard that lets an AI model use your tools and data in a controlled way: look up a case file, create a record, query a database. I build MCP servers and clients. A detailed explanation, with a video: MCP explained simply.

Can Claude create explainer videos?

Yes, since October 2026, with Claude Motion, in beta on the Team and Enterprise plans: Claude writes a short animation as code from your content, editable down to the detail, then exportable as MP4. It is not generated video. The full rundown, with a video: Claude Motion explained.

Can AI read scanned documents?

Yes. OCR extracts the text, then the AI picks out the useful information (names, dates, amounts, business fields) and sends it to your software. That is what I put into production in an ERP for private clinics.

Where should an AI project start?

With one specific, measurable use case. A prototype on your real data quickly shows what AI brings, before you go further.

Let's talk about your project.

Describe what you need in a few lines, or send the brief you built above: I'll reply with a first opinion and the next steps, no strings attached.

Other expertise areas