New Relic Launches Autopilot Kubernetes Agent for AI-Driven Cluster Troubleshooting

Salt Lake City -- New Relic introduced the New Relic Autopilot Kubernetes Agent at KubeCon + CloudNativeCon North America 2026. This AI agent aims to assist site reliability engineers (SREs) and platform engineers in troubleshooting Kubernetes clusters without requiring deep specialized knowledge. The agent is an extension of New Relic Autopilot, a suite of SRE agents that investigate incidents and speed up response workflows.

The agent runs over 90 specialized diagnostic detectors across Kubernetes events, object descriptions, logs, and APM traces to pinpoint root causes. It then produces context-aware remediation code for engineers to review and execute. The agent leverages New Relic's Ground Truth context engine, which assesses correlated operational data built on OpenTelemetry.

New Relic claims the agent can diagnose both common and complex infrastructure failures, such as noisy neighbors, compute resourcing, scheduling issues, network errors, and cloud misconfigurations like Application Load Balancer (ALB) or ingress problems. The agent seamlessly integrates into existing SRE and platform engineering workflows, and offers human-in-the-loop options, ensuring engineers maintain oversight during investigations.

Brian Emerson, New Relic's chief product officer, stated, "When critical Kubernetes infrastructure fails, engineers need clear answers, not just more alerts." The New Relic Autopilot Kubernetes Agent is currently available in public preview.