Working with AI
Alban Pasquelin builds software that agents can drive: AI Desktop Studio exposes 310 actions over the MCP protocol across 26 families, and a specialised Qwen model executes them locally on Apple Silicon, measured by an automated evaluation harness.
Plenty of companies bolt a chat box onto their product and call it AI. Making a product genuinely drivable by an agent takes far more.
AI Desktop Studio is built the other way round: everything a human can do in the application, an agent can do too. Three hundred and ten actions, exposed over the MCP protocol and grouped into twenty-six families. An agent opens a project, generates a texture, applies it to a 3D object and exports the result, with no hand on the mouse.
The model that runs them lives on the machine, with no remote service. It was specialised to understand those exact actions across several languages, and it is re-measured on every version: a new one ships only when the evaluation proves it beats the old one. Without that measurement, tuning a model is guesswork.
In an AI product, the model call is the easy part. The work is in the ninety percent around it: deciding what the agent is allowed to do, recording what it did, and recovering cleanly the moment it gets something wrong.
With AI, under control
I use AI every day to write, test and review code, and you get the benefit: more work delivered for the same budget.
- I review and test everything I deliver, and I stay accountable for it.
- Your code goes through no tool you have not approved.
- If it is sensitive, I work with models that run locally: not a line leaves the machine.
Method
- An agent that can break nothing is useless; an agent that can break anything is an incident waiting to happen. Permissions get designed before features.
- Everything an agent does has to be traceable and reversible.
- A local model costs more to set up and far less to run, and the data never leaves the machine.
- An improvement you cannot measure did not happen.