We're currently deep in the cycle of every enterprise-adjacent company integrating a large language model into its services. Today, New Relic is throwing its hat in the ring with New Relic Grok, which it calls the "world’s first generative AI assistant for observability" (and I'm sure it won't be the last). Unsurprisingly, the idea here is to use a large language model to help engineers use natural language to perform many routine tasks in New Relic -- think setting up instrumentation, building reports and managing accounts.
Image Credits: New Relic
“Observability tools exist to serve the DevOps and DevSecOps movements. Engineers use observability tools to get the data they need to operate and secure the software they build," said New Relic Chief Product Officer Manav Khurana. "The reality, however, is that it's hard for every engineer to translate a question they have into a data model, sift through their tools to find the right data, and then translate data back to an insight in natural language. That's why DevSecOps practices are lagging behind all the innovation in Observability tooling. Now with Generative AI, there will be an explosion of new software developed in a completely different way, creating even more complexity to operate and secure software."
A significant advantage of using these models is obviously to make it easier for engineers to analyze the large amounts of data that the service collects. As Khurana noted, these days, that means not just ensuring the performance of a given service but also the cost of running them, something that's now top of mind for most enterprises.
Image Credits: New Relic
With Grok, engineers can sift through all of this data more easily and comb through their unified telemetry data without having to write complex queries. And while building dashboards and reports will surely be one main use case, Grok will also allow users to use queries like "Why is this service not working?" and get to the root cause of a given problem and use CodeStream, the company's telemetry and collaboration service that can be integrated into popular IDEs, to debug code-level issues if needed.
"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. "Despite the collective progress, engineers are unable to realize the true potential of observability due to the complexity of manually analyzing troves of telemetry data emitted from increasingly complex software systems. New Relic Grok democratizes access to data and insight, and is a game-changer for organizations committed to building agile, innovative, and lasting businesses."
Earlier this year, New Relic also launched its MLOps observability platform, which allows engineering teams to monitor applications built with OpenAI's GPT APIs.
Grok will soon be available in a limited preview.