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.
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.
AI
The rest of this area.
Understand, suggest, and act inside rules you set — with the evidence shown.
Understand
What is this customer actually asking, and about what?
Suggest
A drafted reply, with the evidence it rests on.
Act
Approved actions, inside rules you define.
Confidence
Knowing when not to answer.
Autonomy rules
Exactly what it may handle without a person, decided by you.
Where answers come from
Every claim cites the record behind it.
What it will not do
The line between helping a team and replacing a judgement.
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]