Post

Got to talk at @aidotengineer.bsky.social conf last week about the need for collaborative AI engineering. All our current coding agents are single player. We're trying to scale up individual productivity, but creating tons of alignment problems in the process. We have no good tools for...

I just read the essay/talk and wanted to say thank you. It crystallized something I've been circling for a while. I've been writing about what happens when you treat strategy itself as a protocol: explicit decision logic, written in plain text, readable by people and executable by machines.

My argument is: arguing that the real bottleneck isn't capability but articulation: you can't delegate what you can't make explicit. Your talk makes the same case for teams: the bottleneck isn't code production, it's shared context.