What I'm really building

The products are a consequence. I'm rebuilding the way I work itself to get to the main thing: products that find their people and get bought.

I have a full-time day job, a family, two children — and still many tasks running in parallel and carried through to a result. It isn't about the number of hours: alone and by hand, that much doesn't get done. Hence the bet on agents. I don't write code line by line — I draw up a plan of work, and AI agents carry it out; once, twelve such plans ran in parallel in a single night — thirty-six hours of autonomous agent work in total. Such sessions keep getting longer; that is where the whole industry is moving, and I use it to the full. An agent does the review too: it walks the finished screens in a browser and corrects what it finds, leaving me a short list for a final manual check. The machine does the work; the decisions — what gets done, how and why — stay with me.

My voice notes are turned into a knowledge base automatically: projects, people, decisions, milestones. This timeline is its direct product: I didn't recall the dates, I queried them.

The number of projects is not the goal. The goal is useful products people pay for: to find, among all of this, the ones that genuinely help people, find their audience and are worth the money. What is still missing is the last step — a steady source of traffic, so that the product gets found without me. That's what I'm learning now.

Where I'm heading is a one-man company: a living, profitable business with real customers, real revenue and unit economics that work, scaled by technology and AI agents. As soon as one of the products finds its audience and starts to grow, I'll scale that one — and if that takes people, I'll build a team around it.