AI
Let it handle the routine.
Opening hours, how-to answers, order status, documented product behaviour, sending an invoice a customer is entitled to. Narrow, verifiable, reversible — and configured by you rather than assumed.
An allow-list, never a judgement call
The actions the assistant may take are enumerated. It does not reason about whether something seems safe; it checks whether it is on the list.
Refunds, cancellations and access never qualify
Anything touching money, contracts, account access, complaints or personal data goes to a person. That is structural, not a default you can switch off.
Every action is on the case
What was done, under which rule, with what evidence. An autonomous action nobody can audit afterwards is an autonomous action you should not have enabled.
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.
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.
Permissions
The assistant inherits the asker's access exactly.
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]