What I'm doing now

Updated February 2026. This is a .


Deploying agents inside organizations

Most of my time goes into figuring out how to deploy AI agents within real teams. Not demos, not proofs of concept. Actual agents that people use daily to get their work done.

I'm using , an open-source agent framework, as the foundation. Each team gets their own agent with its own identity, tools, and knowledge. A marketing team's agent is completely different from a customer support agent or a QA agent. They live on a server, they're always on, and team members talk to them through Discord or Slack like they would talk to a colleague.

The interesting part isn't the technology. It's figuring out what each team actually needs versus what sounds cool in a demo. Most agent projects fail because nobody understands the work the agent is supposed to do. I do, because I've done that work for years. That's the edge.


Building my own productivity system

I'm also building my own agent-powered productivity system. The idea is simple: I want an agent that helps me stay organized, track what I'm working on, and surface the right things at the right time. If it works well, it will also help me share more of what I'm doing publicly.

Right now I'm so deep in building that I don't find enough time to document and share the process. That's the bottleneck I'm trying to fix.


YouTube

I'm making videos about what I'm discovering. Not polished tutorials or "top 10 AI tools" lists. More like: here's what I'm actually building, here's what went wrong, here's what I think it means.

The channel has 32K subscribers, which still feels surreal. It grew slowly from years of just making stuff. I'm fine with slow growth. I'd rather say something useful than something clickable.


Thinking about

What does marketing even look like when agents can do most of the execution? I keep coming back to this question.

My working theory: the value moves to strategy, taste, and system design. Knowing what to build matters more than being fast at building it. The agents handle speed now. Humans handle direction.

I don't have it all figured out. Probably won't for a while. But I think the people who are in the middle of it right now, actually building and deploying agents, will understand it first. That's the bet I'm making.


Life stuff

Living in the French countryside near Brive. My wife and I are expecting our first child this summer. That's the forcing function for everything. Every decision I make right now has to work for a family, not just for me.

When I'm not working, I'm usually playing Arma with friends, reading about astrophysics, or walking the dog.