New Relic

New Relic has made several previously announced capabilities generally available, including AI Observability for LLM pipelines and vector databases, ChatGPT Apps Monitoring, eBPF network metrics without added instrumentation, New Relic Knowledge for fusing telemetry with incident history, Mobile Session Replay, and Notebooks for repeatable investigative queries; it also released Preflight, an open source feature giving real-time and historical observability into AI coding agents such as token spend, call volumes, cost forecasts, and tool-selection quality directly in the IDE. This is not a breaking change, so no existing configurations need to be modified to continue using the platform as before.

Matters for: Enterprise SRE and platform teams responsible for production stability who are deploying AI-generated code without line-by-line manual verification and need to detect and reduce resulting incidents, often called agent debt.

New Relic now offers Autopilot, an out-of-the-box automated SRE agent that triages incidents, identifies root causes, and scopes remediations starting from alert firing, and Ground Truth, a set of agent-optimized tools that give external AI agents like GitHub Copilot, Claude Code, or custom orchestrators direct API access to New Relic's observability data. Previously teams lacked a built-in automated incident-triage agent or exclusive API-level tools for grounding third-party agents in New Relic data; this is a non-breaking addition, so no existing configurations need to change.

Matters for: Engineering and SRE teams running Kubernetes and Kafka workloads who want to integrate existing AI agents or orchestrators like GitHub Copilot, Claude Code, or AWS DevOps with their observability data.