AI
You decide what it may do alone.
Four settings, from suggestions only through to handling selected routine requests. Most companies should start at the first and move one step at a time, and the product says so rather than pushing for automation.
Start with suggestions only
The recommended starting point, and the one the setup flow proposes. Everything drafted, nothing sent, for as long as you want.
Widen by category, with evidence
Before enabling a category, you see how it would have performed on real past cases. Enabling autonomy blind is how a support team finds out the hard way.
One switch turns it all off
During an incident, a pricing change or anything unusual, a single control returns everything to suggestions. That switch exists because it will be needed.
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.
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]