Being able to codify these important-but-often-forgotten workflows in such a way that you can set-it-and-forget-it and keep shipping at multi-agent speed is pretty dope.

interesting, I'd like to know how it pairs with existing processes and tools though, since I'm using a fairly heavily optimized pi-agent setup already.

the working spec is files like `.agents/daemons/<name>/DAEMON.md` and they have access to skills and rules in the repo so you don't need to duplicate them.

you could even have a daemon that just says to run an existing skill.

Outstanding. Exactly the setup I was looking for.

How is this different than a trigger set up?

it's similar to triggers, but with a routing layer that combines semantic triggers and memory. the magic is defining them as files in the repo (like skills) and not worrying about the execution.