What can an AI agent do with PagerDuty?

A PagerDuty AI agent can list and read incidents across services, fetch on-call schedules, browse service health, pull alert details for root cause analysis, acknowledge active incidents, and add notes to incidents. Write actions like acknowledging incidents or adding notes require your approval.

Which incidents and services can my agent access?

Your agent accesses whatever your connected PagerDuty account can see. You can scope tasks to specific services, teams, or urgency levels by naming them in the task instructions.

Can my agent automatically acknowledge or resolve incidents?

Yes, but acknowledging and resolving are write actions that require your approval in safe and plan permission modes. You can configure auto-approval for trusted recurring workflows.

How is a PagerDuty AI agent different from PagerDuty's built-in alerts?

PagerDuty alerts fire on thresholds but can't reason across incidents or explain patterns. A PagerDuty AI agent reads the full incident queue, groups related alerts, and produces a plain-language summary of what's happening, who's on call, and what needs attention next.

Developer tools

PagerDuty, run by an agent.

An AI agent that monitors incidents, surfaces on-call activity, and summarizes alert trends.

Connect PagerDuty Book a demo

What needs your approval

PagerDuty never changes anything without you.

Anything that creates, edits or deletes in PagerDuty waits for your approval. Approve a recurring task once and it runs unattended after that.

Connecting PagerDuty

About 5 minutes

Auth: API key
Setup: About 5 minutes

Where to get access

Create an API key in PagerDuty under Integrations > API Access Keys.

support.pagerduty.com

Example tasks

Real work people hand to an agent that uses PagerDuty.

generate a daily incident summary and post it to Slack with open vs resolved counts
monitor for new high-urgency incidents and page the right on-call responder
summarize on-call activity for the week including incident volume and mean time to resolve
triage a noisy alert spike by grouping related incidents and identifying the affected service