Status: in active daily use, unproven. This is the system I run my own work on — not a product for sale, and not a finished bet. Screenshot shows my own dashboard.
Most of this blog is about a thing I keep calling the factory, as if it were just the workshop where the real products get made. The ad platform, the health assistant, the video app — those are the products. The factory is the bench they sit on.
I have had that backwards.
The factory is the project. It is the most ambitious thing I am building, and the products are partly a way of proving it works.
Strip away the name and the factory is a way for one person to do what used to take a team. Not by working harder, and not by one clever AI that does everything. By a system.
The system is made of unglamorous parts, and I have written about most of them one at a time. A set of rules the agents read before they touch anything, so they stop guessing where I was unclear. A team of agents with real jobs — some build, some review, some are paid only to find what is wrong — and a standing rule that none of them gets to mark its own work done. Gates that physically stop work that has not proven it works, instead of polite notes asking it to behave. A memory, so what one session learns the next one starts from. A meter that shows what the agents are spending before the bill does. A dashboard where I can see every product at once and step in only where I am actually needed.
None of those is impressive by itself. Together they are the thing. They are what lets me hand real work to agents and trust what comes back — and trust is the only thing that makes the volume possible.
What the volume actually looks like right now: six products under one roof, hundreds of commits a month, run by one person. None of that is a pace I could touch by hand. It only exists because the agents do the building and the system keeps them honest enough that I can let them.
Whether that actually holds up is the open part. Whether the rate truly compounds, or whether I am just generating a lot of motion that looks like progress — I am still finding out. None of the products is finished. None of this is proven. It is a bet I am in the middle of, not a result I am reporting. The reason to write it down now, while it is uncertain, is that the honest version is the one worth reading.
Why it matters more than any one product
A single product is a bet on one idea. The factory is a bet on the rate.
If the system is good, the next product is faster than the last, because the rules are already written, the agents already know their jobs, the gates already catch the same mistakes, and the memory already holds what the last build learned. Each product makes the factory better, and a better factory makes the next product cheaper. That compounding is the actual asset. The products are how I find out whether it is real.
That is also why so much of my time goes into things that never show up on a screen — sharpening a rule, writing down yesterday’s mistake, building one more gate. It looks like I am not shipping. I am building the thing that ships.
Learnings
I set out to build an assistant and ended up building the thing that builds. For a long time I treated that as a detour — the factory was overhead, the products were the point. The honest version is the reverse. Any one product can succeed or fail. The factory is the bet that one person, with the right system around a set of capable agents, can run a portfolio that used to need a team for each line of it.
The reason I keep investing in the boring parts — the rules, the gates, the memory, the meter — is that they are not boring at all once you see them as the product. They are the difference between an AI that does impressive demos and a system you can actually trust with real work, real money, and more than one thing at a time. That trust, built deliberately and in the open, is the project. Everything else is something the project made.