New Relic announced New Relic Grok, a generative AI assistant for observability.
New Relic Grok reduces the toil of manually sifting through data, makes observability accessible to all regardless of prior experience, and unlocks insights from any telemetry data source. Leveraging OpenAI’s large language models (LLMs) and New Relic’s unified telemetry data platform, New Relic Grok allows engineers to use natural language prompts to perform tasks previously done via traditional user interfaces—setup instrumentation, troubleshoot issues, build reports, manage accounts, and more. This accelerates New Relic customers’ efforts to consolidate telemetry data in its platform, increases the volume of queries that uncover insights, and enables new teams to adopt observability.
“Ever since we invented cloud APM in 2008, we have pioneered innovations years ahead of competitors. New Relic Grok is the continuation of this DNA and defines how generative AI will transform our industry,” said New Relic CEO Bill Staples. “New Relic Grok makes observability dramatically simpler, democratizes access to instant insights, and helps engineering teams realize the true potential of observability.”
New Relic Grok serves high-quality insights by deploying generative AI to a hyper scaled and unified telemetry data source, enables engineers to easily understand complex systems, and makes observability accessible to every engineer regardless of prior experience. As the vision of generative AI is realized, it fuels tool and data consolidation onto New Relic, a platform that runs on a unified data source for all telemetry from all services monitored.
New Relic Grok will allow all engineers to:
- Setup instrumentation and monitoring: Identify instrumentation gaps and provide instructions on instrumenting services, set up missing alerts, and automate alerts using Terraform.
- Isolate the root cause: Use chat to ask anything, such as “Why is my service not working?,” and New Relic Grok will analyze piles of telemetry data and recent changes to identify the root cause.
- Debug code-level issues: With CodeStream and errors inbox, New Relic Grok automatically pinpoints code-level errors in the IDE and analyzes code, stack traces, and production telemetry to suggest fixes.
- Generate reports and dashboards: With just a few words, anyone can generate a system or app health report complete with anomalies, issues, and recent deployments. No more trying to filter dashboards.
- Natural language queries: Use plain language (in more than 50 languages) to craft analysis queries and translate query results into simple explanations for easy sharing with all teams, including executives.
- Manage admin tasks: Let New Relic Grok manage your account, users and user access, data retention rules, usage, billing, and more.
New Relic Grok comes on the heels of New Relic’s machine learning operations (MLOps) capability that allows engineering teams to monitor applications built with OpenAI’s GPT Series APIs. The AI assistant will be available soon via a limited preview as part of the New Relic all-in-one observability platform.
The Latest
In MEAN TIME TO INSIGHT Episode 24, Shamus McGillicuddy, VP of Research, Network Infrastructure and Operations, at EMA discusses network observability tool sprawl ...
In cloud-native systems, scaling is often as simple as moving a slider. For on-premise databases, the stakes are different. Over-provisioning hardware is expensive. Under-provisioning leads to performance bottlenecks that are difficult to fix once the equipment is in the rack ...
When most people think about cybersecurity, they picture firewalls, encryption, and access controls — technical tools designed to protect systems and data. But beneath the technology lies a deeper set of principles about trust, decision-making, and resilience ... The best leaders don't eliminate risk. They manage it intelligently. And in many ways, cybersecurity offers a surprisingly useful playbook for doing exactly that ...
Many organizations assumed their infrastructure strategy was settled. It had been implemented, optimized and built into long-term plans. Recent changes in technology and vendor consolidation are forcing a second look. Cloud outages and licensing changes have exposed how much dependency exists on a small number of platforms. As a result, organizations are reevaluating whether those decisions still hold up under current conditions ...
Edge AI is strategically embedded in core IT and infrastructure spending across industries, according to the 2026 Edge AI Survey from ZEDEDA. The research shows that 83% of C-suite and IT executive respondents say edge AI is important to their core business strategy ...
As AI adoption accelerates, operational complexity — not model intelligence — is becoming the primary barrier to reliable AI at scale, according to the State of AI Engineering 2026 from Datadog ... The report highlights a compounding complexity challenge as AI systems scale ... Around 5% of AI model requests fail in production, with nearly 60% of those failures caused by capacity limits ...
For years, production operations teams have treated alert fatigue as a quality-of-life problem: something that makes on-call rotations miserable but isn't considered a direct contributor to outages. That framing doesn't capture how these systems fail, and we now have data to show why. More importantly, it's now clear alert fatigue is a symptom of a deeper issue: production systems have outgrown the current operational approaches ...
I was on a customer call last fall when an enterprise architect said something I haven't been able to shake. Her team had just spent four months trying to swap one AI vendor for another. The original plan said three weeks. "We didn't switch vendors," she told me. "We rebuilt half our integrations and discovered what we'd actually been depending on." Most enterprise leaders don't expect that to be the experience ...
Ask any senior SRE or platform engineer what keeps them up at night, and the answer probably isn't the monitoring tool — it's the data feeding it. The proliferation of APM, observability, and AIOps platforms has created a telemetry sprawl problem that most teams manage reactively rather than architect proactively. Metrics are going to one platform. Traces routed somewhere else. Logs duplicated across multiple backends because nobody wants to be caught without them when something breaks. Every redundant stream costs money ...
80% of respondents agree that the IT role is shifting from operators to orchestrators, according to the 2026 IT Trends Report: The Human Side of Autonomous IT from SolarWinds ...