Blab AI
New Relic Launches Autopilot and Ground Truth to Power AI-First Incident Management
On 23 June 2026, New Relic announced two AI‑driven additions to its observability suite designed to lift the load on site‑reliability engineering (SRE) teams.
The first, Autopilot, is an out‑of‑the‑box SRE agent that lives on New Relic’s telemetry data. As soon as an incident fires, the agent triages alerts, isolates root causes, and suggests remediation steps. It brings built‑in domain expertise for Kubernetes and Kafka, and can perform cross‑stack root‑cause analysis. By ingesting an organization’s runbooks and retrospectives, and by pulling code context from Jira and GitHub through the Model Context Protocol (MCP), Autopilot learns the nuances of each team’s workflow. Users can access the agent via the New Relic platform, Slack, or automated actions that trigger on a SEV‑1 alert, a deployment, or on a schedule.
Ground Truth, the second offering, opens a set of APIs that let customers’ own AI agents—whether GitHub Copilot, Claude Code, AWS DevOps, or custom orchestrators—query New Relic’s deepest observability data. The APIs expose premium insights that are hard to reach through public endpoints or simple query tools, allowing agents to locate relevant information more efficiently and with fewer token‑costly calls. A large enterprise that tested Ground Truth reported a 1.1 % error rate across more than 1,300 users.
"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."
The announcement comes after New Relic’s 2023 acquisition by private‑equity firms Francisco Partners and TPG for roughly $6.5 billion, a deal that has positioned the company to expand its AI‑enabled observability services.
Industry analysts see the launch as part of a broader shift toward agentic AI, where autonomous agents perform routine operational tasks without human intervention. By providing a shared data substrate and API‑based integration points, New Relic aims to lower the barrier for enterprises to adopt AI‑driven incident response while preserving the depth of telemetry that SRE teams rely on.
The company’s AI‑first strategy also dovetails with its earlier 2026 release of an Agentic Platform that lets organizations build, deploy, and manage a spectrum of AI agents—from simple automations to complex workflows. Autopilot and Ground Truth extend that platform by offering pre‑built, domain‑specific expertise and a direct channel to the observability data that underpins modern cloud‑native stacks.
Current deployments of Autopilot are limited to a small set of Kubernetes‑centric workloads, with plans to add more domain specialists in the coming months. Ground Truth is already available to customers with existing AI agents, and New Relic is working with partners such as GitHub and AWS to streamline integration.
The launch underscores the growing importance of observability data as a foundation for AI‑powered operations. By enabling AI agents to reason directly from telemetry rather than dashboards, New Relic seeks to reduce incident response times and lower mean time to resolution for enterprises that are increasingly adopting agentic workflows.
As AI‑first businesses continue to scale, the ability to ground autonomous agents in reliable, real‑world data will likely become a key differentiator. New Relic’s Autopilot and Ground Truth are positioned to serve that need, offering both a managed solution and a plug‑in for existing AI ecosystems.
The company has not yet disclosed pricing for the new capabilities, and it remains to be seen how quickly adoption will spread across its customer base. However, the announcement signals a significant step toward integrating AI more deeply into observability and incident management.
The first, Autopilot, is an out‑of‑the‑box SRE agent that lives on New Relic’s telemetry data. As soon as an incident fires, the agent triages alerts, isolates root causes, and suggests remediation steps. It brings built‑in domain expertise for Kubernetes and Kafka, and can perform cross‑stack root‑cause analysis. By ingesting an organization’s runbooks and retrospectives, and by pulling code context from Jira and GitHub through the Model Context Protocol (MCP), Autopilot learns the nuances of each team’s workflow. Users can access the agent via the New Relic platform, Slack, or automated actions that trigger on a SEV‑1 alert, a deployment, or on a schedule.
Ground Truth, the second offering, opens a set of APIs that let customers’ own AI agents—whether GitHub Copilot, Claude Code, AWS DevOps, or custom orchestrators—query New Relic’s deepest observability data. The APIs expose premium insights that are hard to reach through public endpoints or simple query tools, allowing agents to locate relevant information more efficiently and with fewer token‑costly calls. A large enterprise that tested Ground Truth reported a 1.1 % error rate across more than 1,300 users.
"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."
The announcement comes after New Relic’s 2023 acquisition by private‑equity firms Francisco Partners and TPG for roughly $6.5 billion, a deal that has positioned the company to expand its AI‑enabled observability services.
Industry analysts see the launch as part of a broader shift toward agentic AI, where autonomous agents perform routine operational tasks without human intervention. By providing a shared data substrate and API‑based integration points, New Relic aims to lower the barrier for enterprises to adopt AI‑driven incident response while preserving the depth of telemetry that SRE teams rely on.
The company’s AI‑first strategy also dovetails with its earlier 2026 release of an Agentic Platform that lets organizations build, deploy, and manage a spectrum of AI agents—from simple automations to complex workflows. Autopilot and Ground Truth extend that platform by offering pre‑built, domain‑specific expertise and a direct channel to the observability data that underpins modern cloud‑native stacks.
Current deployments of Autopilot are limited to a small set of Kubernetes‑centric workloads, with plans to add more domain specialists in the coming months. Ground Truth is already available to customers with existing AI agents, and New Relic is working with partners such as GitHub and AWS to streamline integration.
The launch underscores the growing importance of observability data as a foundation for AI‑powered operations. By enabling AI agents to reason directly from telemetry rather than dashboards, New Relic seeks to reduce incident response times and lower mean time to resolution for enterprises that are increasingly adopting agentic workflows.
As AI‑first businesses continue to scale, the ability to ground autonomous agents in reliable, real‑world data will likely become a key differentiator. New Relic’s Autopilot and Ground Truth are positioned to serve that need, offering both a managed solution and a plug‑in for existing AI ecosystems.
The company has not yet disclosed pricing for the new capabilities, and it remains to be seen how quickly adoption will spread across its customer base. However, the announcement signals a significant step toward integrating AI more deeply into observability and incident management.
