Skip to content
← AI

AI

No back door, by construction.

The assistant has no view of its own. It queries as the person asking, through the same checks, which is why there is no second permission model to keep in step.

Inherited identityCustomer scopeOpt-in sensitivityLogged

One model, not two

A parallel AI permission set would eventually diverge from the real one, and the divergence would be a data breach. So there is only one.

Customers get a narrower set again

The assistant in the help centre and the portal answers as that customer, scoped to that customer's own account and to published knowledge only.

Sensitive categories are opt-in

Complaint records, legal correspondence and anything flagged sensitive are excluded from assistant answers by default, even for people who could open them directly.

Take better care of every customer.

Give your team the context, knowledge and AI they need to resolve problems properly — and know who needs attention before they ask.

Keep the mailbox you already use · The AI is never metered · [email protected]