PagerDuty Inc. introduced Paige, an SRE agent built to work as a member of operations and engineering teams. Paige runs on the company's flagship product, now called the PD Reliability Platform, which was previously known as PagerDuty Operations Cloud. PD Labs is a new program for putting early features in front of customers while they are still being built.
Customers set Paige's permissions team by team. Teams that keep a person in the loop get faster triage with remediation held for approval, while the agent acts on its own only in low-risk scenarios the team has explicitly authorized. Paige can be added to escalation policies as a virtual responder, and lower-priority incidents may never reach a human.
PagerDuty also released a new console showing incidents, on-call rotations and AI agents in one view, and says Paige beat leading AI coding agents at diagnosing simulated IT incidents in a benchmark it published. Paige and the platform are generally available, and SRE Workbench is available to try through PD Labs. Three PD Labs experiments are in preview: Topology, Deep Investigation and SRE Workbench.
Why it matters if you build agents
Teams building agents that run alongside on-call engineers can now grant Paige per-team permissions, with approval gates for remediation. Incident memory is shared across incidents, so resolved issues feed future diagnosis.
If your agents touch production systems, check how Paige's authorized low-risk actions would interact with your own automation before enabling it on a team.
Get stories like this every weekday
One short email with the day's agent tooling news.