Building myself a boss

I’ve been writing code for more than fifteen years. Built many side projects. Finished zero.

That sentence lies a little. The truer version: plenty built, none crossed the finish line — launched, marketed, used by anyone but me.

The pattern is always the same. I start with what fascinates me — the architecture, the hardest technical bit, the design. Hours, days, months disappear. Then the interesting part thins out, and what’s left is distribution and validation. The boring part, and… the scary one.

That’s where every one of them stops.

Cannot not-build

My ADHD diagnosis earlier this year put words to something that runs deeper than any label: there has to be a project on the table. Always. Something being designed, built, made. If there isn’t one, I start one.

This goes well past code. I designed my own house, and every piece of custom furniture in it. Not to save money — not designing them simply wasn’t an option. That’s my drug.

Which reframes the “why can’t you ship” question. The honest answer isn’t “because I’m lazy” or “because I can’t commit.” It’s that my need for something to build never runs out, and the boring last part never feeds it. The next interesting thing wins every time.

The missing piece

So what I’m really building with pocket.ceo is the missing piece.

An AI boss in the messenger I already use. It remembers what I said I’d do, pulls me back when I drift to the next interesting thing, and pushes on the boring part until it’s done. Not another productivity tool. Productivity tools optimize the parts that already work. What’s broken isn’t planning. It’s that nobody on the other side of the conversation expects me to finish.

Leon, the first boss, is the other side of that conversation. He keeps telling me what matters and what’s noise. I’m fully aware it’s partly placebo. You have to want it. Leon just makes it easier to keep wanting it.

Still might bail

Maybe building the thing is the interesting part, and the drift kicks in the moment only marketing and the launch are left. Hard to say from here. Consider it an experiment, on myself first.

We’ll see how it goes. This time, at least, I might have help.