New Relic unveils two complementary innovations that aim to provide holistic visibility into interconnected agents and tools, and enable an ecosystem of agents for advanced agentic workflows.
“The convergence of AI workloads, cloud-native architectures, and real-time data processing has created a perfect storm of complexity,” said New Relic chief product officer Brian Emerson. “Our platform uses intelligent automation and unified data correlation to diffuse that complexity so you can operate your business confidently and at scale. Our latest innovations further empower enterprises to adopt AI systems that create real business value, rather than cutting into the bottom line.”
Observability for Agentic AI
New Relic Agentic AI Monitoring aims to provide visibility into every agent and tool call within multi-agent collaborations for a better understanding of how agents communicate with each other. It also seeks to provide insights into tool utilisation, performance, errors, and key performance data.
Beyond monitoring individual LLMs, the solution claims to provide holistic observability across interconnected agents, tools, services, and infrastructure they rely on. Built on top of New Relic’s APM and infrastructure monitoring tools, the solution can help pinpoint issues faster, accelerate root cause analysis, and optimise performance across their entire AI-enabled stack.
New Relic AI MCP Server
The New Relic AI MCP Server allows engineers to retrieve data and insights from wherever they’re working, eliminating context switching and enabling faster incident response, shorter MTTR, better uptime, and accelerating time-to-market. It democratises observability by allowing users to ask questions and receive actionable insights promptly.
Outlier Detection
New Relic's Outlier Detection is a proactive tool that can highlight data points signalling issues or failures, as well as suspicious behaviours. It goes beyond flagging outliers, streamlining remediation and enabling teams to address incidents before they affect end users.
