Operations | Monitoring | ITSM | DevOps | Cloud

As we look at the role AI can play in Grafana going forward, we want to move beyond the simple chat responses that dominate the world of LLMs today and into agentic systems—AI that can understand, reason, and act on your behalf. The ultimate goal is to make it easy to get things done in Grafana using natural language—whether you’re a seasoned SRE or a new developer. And in the AI world, we call this moving from chat completion to task completion.

Every second counts when it comes to detecting, diagnosing, and resolving network incidents, yet many teams still find themselves stuck in reactive mode, drowning in alerts, manually writing scripts, and managing tickets across disconnected systems. This is where Selector and Itential come in. Together, Selector and Itential deliver a powerful, enterprise-ready solution that closes the loop between detection and action.

AI has emerged as a defining force in modern technology, spearheading transformation across industries. Yet, despite its promise to revolutionize workflows and unlock unprecedented efficiency, most DevOps organizations face significant hurdles in adopting AI safely and effectively. Concerns about complexity, scalability, and governance hold many decision makers back.

Four months ago, Claude Code was announced and we were requesting invites to its "Research Preview." Now? We've gone from no Claude Code to simultaneously running four or five Claude agents, each working on different features in parallel. It sounds chaotic, but it's been a natural progression as we've learned to trust AI more and as the tools have dramatically improved.

Cybercriminals are no longer lone hackers sitting behind screens; they use artificial intelligence to supercharge their attacks. They employ large language models (LLMs) that generate phishing content to evade human detection. They use malware that adapts mid-execution to bypass sandbox environments and deepfake video/audio to mimic executives in real time.

AI is changing how we build software — but debugging code still comes down to having context. One minute the model’s performance is cruising. The next, you’re hit with a KeyError from a tool you forgot existed, triggered by a model that silently timed out, and a retrieval call that returns... nothing, or 11 “Let me try this a different way" messages before failure. You’re stitching together LLM calls, agents, vector stores, and custom logic. Then hoping it holds up in prod.