Software, built by agents.
A factory of agents does the work. Your experts set the direction and decide what matters.
The bottleneck was always the people.
Every AI tool so far still puts a person in the loop, so the whole line waits on them. Take people off the line and nothing waits anymore.
Four ideas the factory is built on.
What a run looks like.
One screen for the whole run. You watch the work move, and step in wherever a decision needs you.
Same task. We get all of it done.
Give one model a real task and it only ever gets through part of it. There is more there than it can hold at once. Split the same task across many small agents, each on its own piece, and the whole thing gets done. Same task, far more finished.
358 agents against your codebase, for less than a single frontier session.
Running this many agents at once only makes sense if each one is cheap to run. So we built our own inference stack for it: most of the work runs on small models we train in-house, and the frontier model gets called in only where it actually pays off.