New Relic, the Intelligent Observability Company, announced the next evolution of its platform that will power agentic AI-first businesses. The New Relic Autopilot and New Relic Ground Truth capabilities provide engineering teams with ultimate flexibility, enabling them to either deploy an automated SRE agent operated entirely by New Relic or supercharge their existing, custom AI agents by natively integrating them with New Relic’s powerful observability data substrate.
"Operations are going headless. AI agents won't log in to view dashboards. They'll pull what they need through APIs, reason about it, and act," said Camden Swita, Head of AI at New Relic. "That's exactly what New Relic Ground Truth delivers: it grounds your own agents in the real truth of your systems, through APIs instead of UIs. And for teams who'd rather we run the agent, there's New Relic Autopilot, our expert agent operated for you. Both sit on the same rich data substrate, and either way the toil is reduced."
New Relic Autopilot: Out-of-the-Box Automated SRE Operations
The challenging aspect of an incident is not identifying what broke, but pinpointing why, whether it is safe to act and next steps. The New Relic Autopilot capability is an out-of-the-box automated SRE agent built on New Relic's data substrate that automatically triages incidents, identifies root causes, and scopes possible remediations. It starts with analysing the moment an alert fires, giving human responders a significant advantage early on in the response process and helping them hit service level objectives (SLOs).
Key features of New Relic Autopilot include:
A Growing Team of Expert Agents and Specialised Tools: Features domain specialists in Kubernetes, tools optimised for Kafka troubleshooting and cross-stack root-cause analysis, with more coming soon. Every result is a well-structured account grounded in concrete data and expert insight.
Learns Your Environment: New Relic Knowledge grounds conclusions in an organisation's specific runbooks and retrospectives. External Model Context Protocol (MCP) connections to Jira and GitHub pull in code details to pin down problems.
Long-Term Memory: Captures tribal knowledge and disperses it across the team. Memory can be scoped and managed to optimise agent accuracy.
Works Where You Do: Features a new agentic user experience on the New Relic platform, in Slack, and via automated workflow actions triggered by a SEV1, after a deploy, or on a schedule.
