Who decides when the voice agent calls?

Your escalation policy or workflow. The call is a step you define, with the alerts, people and order. The agent carries out the step and then briefs the engineer.

What happens if nobody answers?

The next step of the escalation policy pages the next person. That decision belongs to the policy your team wrote, not to the agent.

Can the agent make changes during the call?

It can take actions within the access it has been given. It checks with the engineer before paging someone else, escalating, downgrading or muting a monitor, and everything it does lands in the incident record.

Where does the record of the call go?

To the incident timeline: the transcript, the outcome of the call and an AI summary.

The AI call to the on-call engineer

Noci AI's voice agent phones the on-call engineer on its own, as your escalation policy or workflow defines. It tells them what is wrong, who is affected and what has been found, and takes actions during the call. The transcript, the outcome and an AI summary land on the incident timeline.

What happens on the call?

The voice agent replaces one step of an escalation policy: instead of a message, a phone call.

An alert is routed to a policy. The escalation policy chooses who is on call and how to reach them.
The call is placed. The voice agent phones the on-call engineer on its own, as the policy or workflow defines. Nobody has to start it.
It briefs. It says who is calling, what is wrong, who is affected, since when, and what has been found.
The engineer responds. They can ask for detail or tell it what to do next, and the agent takes actions during the call.
The outcome is recorded. The transcript, the outcome and an AI summary go on the incident timeline.

What does it check first?

The voice agent checks with the engineer before it pages someone else, escalates, downgrades or mutes a monitor. Each of those affects other people or hides a signal, so a person decides.

You choose, step by step, whether an agent asks before it acts. See agents and actions.

Why a call, and not only a message?

A call is harder to miss than a message, and it can get an answer in the moment. It is the channel for urgent incidents, especially at night. For something that can wait, a message in a channel is kinder, and the policy can say so. The channels are compared in which channel wakes an engineer. The longer read on what the agent says and how to design the call is how AI voice agents improve incident response.