[Writing]

Notes from inside
the checkpoint.

Short pieces on deterministic authorization, bounded authority, and what governing agentic AI actually requires. Nothing is published yet: we're in stealth, and these are the arguments we're writing up first.

In draftNote 01

Probabilistic enforcement is not enforcement

A model asked to judge whether an action looks acceptable is still guessing. Why the control plane for agentic AI has to be deterministic, and what changes the moment it is.

In draftNote 02

Standing authority is the vulnerability

Every incident pattern we've studied traces back to authority that outlived the action it was granted for. The case for single-use, exhaustible warrants over long-lived credentials.

In draftNote 03

What insurers need before they can price an agent

Underwriting requires a provable record of who authorized what, and when. What that record has to look like, and why it can only be produced at the point of execution.

These go up as they're finished. If you'd like to read them early, or you're working on the same problem, get in touch.

start here

The protocol

The architecture these notes are written against: a deterministic checkpoint in the path of every attempted agent action.

Read the protocol