Great take!

I think the "agents only know what's in training data" argument never made sense to me. I've watched Claude read a markdown skill file and correctly invoke a CLI it had never seen before.

The thing that actually matters is whether your interface is predictable consistent verbs, typed errors, no magic. Agents are surprisingly good at learning from docs, they're just terrible at guessing.

The real question for Plain isn't "will agents know it", it's whether the opinionated defaults actually reduce the surface area they have to reason over. Django's flexibility is kind of a nightmare for agents because there are 6 ways to do everything. If Plain picks one, that's genuinely useful.

Anyway, "designed for humans and agents" is going to be on every framework README by EOY whether it means anything or not, so might as well be the one that actually thought about it first ;P