Behind the Scenes: SRE Agent
What if your first responder never slept, had perfect memory of every past incident, and completed initial triage before an engineer could even open their laptop?
In this live session, our engineering and product teams break down how we built the SRE Agent virtual responder and how recent major enhancements enable teams to achieve autonomous operations through automated triage and investigation.
Who Is This For?
SREs, ITOps and Platform Engineers looking to eliminate repeat pages, Developers and DevOps scaling systems, PagerDuty Admins configuring incident workflows, Engineering Managers, CIOs and CTOs focusing on reduce MTTR and strengthen platform reliability.
What We’ll Cover:
- Workflow Automation & Intelligent Triggers: How the SRE Agent can be dynamically deployed via Incident Workflows to launch triage the moment an alert fires based on severity or priority, saving critical minutes during high-pressure MTTR windows.
- The New Configuration Experience: A first look at setting up Connectors, Tools, and Skills via the API and Model Context Protocol (MCP) to securely plug the agent into third-party telemetry (DataDog, Grafana, New Relic) and knowledge bases (Confluence, GitHub).
- Deep Integration & Claude Plugin: How to design custom operational instructions directly from the Claude marketplace to tailor the agent to your exact production environments.
- Continuous Learning Flywheel: A live look at how the agent leverages the operational memory of past incidents to automatically recommend remediation playbooks, resolving incidents faster and preventing tomorrow’s pages.
Meet the Speakers:
Alexis Chu – Senior IT Product Manager, PagerDuty
Julia Nasser – Senior Principal Product Manager, PagerDuty
Micah Mayo – Software Engineer V, PagerDuty
Host: Daniel Afonso – Senior Developer Advocate, PagerDuty
PagerDuty is an incident management and real-time operations platform powered by AI designed to help teams detect, respond to, and resolve critical issues faster. For developers, PagerDuty streamlines on-call management, automates alerting, and integrates seamlessly with popular tools like Slack, GitHub, and AWS. Whether you’re building, deploying, or maintaining services, PagerDuty empowers engineering teams to minimise downtime, collaborate efficiently, and deliver reliable digital experiences. Learn more at https://www.pagerduty.com/.