Use cases

Businesses need checkpoints. Agents need passports.

It starts at the concrete moment an AI agent wants to act — and someone has to decide whether to trust it.

Where it fits

Six places agent trust breaks down today.

01

Businesses with websites

Add the free checkpoint before unknown agents submit forms, access accounts, or hit paid routes.

02

Hermes users

Passport an assistant before asking it to shop, book, or submit requests for you.

03

OpenClaw and Odysseus users

Prove which AI is acting, who owns it, and what it's allowed to do.

04

Engineering agents

Require approval before repo writes, deploys, incident commands, or infra changes.

05

Ops and finance agents

Put human review in front of refunds, vendor actions, and payment changes.

06

Support agents

Let AI draft and summarize freely — but gate account changes, refunds, and exports.

Pilot workflow

One website action. One passported agent.

01

Register

Create the passport and assign owner, purpose, scope, and expiry.

02

Protect

Route sensitive actions through an Gardien check.

03

Decide

Allow low-risk work, pause risky actions for approval, deny unknown agents.

04

Review

Pull the decision trail when anyone asks what happened.

Next step

A website that needs a checkpoint, or an agent that needs a passport?