Every action runs at an autonomy level you control, from fully manual to fully automatic.
Administrators set the level for each kind of action, and a rule engine can override it for specific situations.
The human does it; the agent stays out of the way.
The agent suggests; the human does the action.
The agent prepares and proposes; the human approves at a decision gate.
The agent acts on its own; the human can watch and intervene.
The agent handles it end-to-end, no human step.
A decision gate is where an agent pauses and asks a human to approve a consequential choice. Approvals collect in the Approval Inbox.
The advisor recommends but resolves nothing; the desk owner accepts at the gate.
Explore the platform in a safe Training sandbox, or book a walkthrough with our team.