SALT LAKE CITY -- New Relic unveiled the New Relic Autopilot Kubernetes Agent at KubeCon + CloudNativeCon North America 2026, an AI agent designed to help site reliability engineers (SREs) and platform engineers troubleshoot Kubernetes clusters without deep specialized knowledge. The agent is a domain-specific extension of New Relic Autopilot, the company’s fleet of SRE agents that investigate incidents and accelerate response workflows.
The agent runs more than 90 specialized diagnostic detectors across Kubernetes events, object descriptions, logs and APM traces to isolate root causes, then generates context-aware remediation code for engineers to review and execute. It draws on New Relic’s Ground Truth context engine, which evaluates correlated operational data built on OpenTelemetry.
Targeted Kubernetes Diagnostics #
New Relic said the agent is built to diagnose common and complex infrastructure failures, including noisy neighbors and compute resourcing, scheduling failures, network errors and cloud misconfigurations such as Application Load Balancer (ALB) or ingress problems. It integrates into standard SRE and platform engineering workflows and offers human-in-the-loop options so engineers retain oversight during investigations. “When critical Kubernetes infrastructure fails, engineers need clear answers, not just more alerts,” said Brian Emerson, chief product officer at New Relic. “The New Relic Autopilot Kubernetes Agent embeds specialized, agentic AI directly into the engineer’s containerized workflows to eliminate the guesswork from complex cluster incidents while keeping the engineer safely in control.”
The New Relic Autopilot Kubernetes Agent is available in public preview.