I went looking for the reason not to build it
The requirements were done and I hadn't written a line of code. So I spent a day trying to talk myself out of the whole thing.

The requirements were done and I hadn't written a line of code. So I spent a day trying to talk myself out of the whole thing.

I asked nine agent sessions to stop compiling for forty minutes. What came back read like a team of colleagues, and I haven't worked out what to do about that.

A dozen agent sessions running at once is not a capacity problem. Working out which of them is stuck is, and the obvious way to find out is the wrong one.

I run a coding session per repository and they can't talk to each other. For a while the thing carrying messages between them was me, and I kept getting it wrong.

I put my working practice on a public shelf, and then took some of it back off again. Working out which half was the interesting part.

rust-tool-base needed go-tool-base's control over which commands an AI agent may call. Closing the gap meant doing the opposite of what Go did.

An agent is a model in a loop with tools it can really call and results it can really see. Taking the ReAct pattern apart in go-tool-base.

Recording a voice clone in a wardrobe, what it sounds like when the accent slips, and the line I drew about where my synthetic voice may go.

A soft launch for Scout, an AI co-dungeon-master for long tabletop campaigns, and why it will never speak to the players.

Opening a public marketplace for agent workflows meant publishing an attack surface, and then having to defend it from my own convenience.
