Operations | Monitoring | ITSM | DevOps | Cloud

Grafana AI Observability is our new database and platform for observing AI Agents. Over the past year at Grafana Labs, we built Agents and we needed a way to understand how they are performing, what are the costs associated with them, what's the error rate or time to the first token as well as how they are behaving. Grafana Staff Engineer, Ivana Hučková provides a deep dive demo on how Grafana AI Observability connects our experience building Agents with our experience building observability systems.

Senior Software Engineer William Dumont demonstrates how we test Assistant Investigations by pitting two versions of the same agent against each other to correctly identify and remediate a production incident we've already resolved.

Thursday is about testing and evaluation. Here's what we're announcing today! Check out grafana.ai for more details on everything we announce this week.

In this video, our Senior Director for AI Engineering, Mat Ryer, issues a challenge: Can k6 agentic testing in Grafana Cloud be instructed at a high level to just beat Wordle? Staff Software Engineer Joan López de la Franca Beltran sets up that scenario using agentic testing (currently experimental), yielding some surprising results.

Staff Software Engineer Alexander Sniffin demonstrates how you can use Assistant Investigations to automatically start an investigation for you when an alert fires in Grafana. When you receive an alert, Investigations can do the work to figure out the root cause so that you don't have to spend your time doing so. Assistant Investigations is now generally available for Grafana Cloud.

Wednesday is about operations and maintenance. Here's what we're announcing today! Check out grafana.ai for more details on everything we announce this week.

Tuesday is about Building and implementation. Here's what we're announcing today! Check out grafana.ai for more details on everything we announce this week.

Your AI agents are only as good as the context it has. Without access to what's happening in production, it can only make educated guesses. Chapters: In this video, you'll meet GCX. The bridge between AI coding agents like Claude Code, Codex, Cursor, and your Grafana observability stack. You will learn how GCX securely gives AI agents access to metrics, logs, traces, dashboards, and other production telemetry so they can investigate issues, answer questions, and help you debug with real operational context.

AI Week has begun! Check out grafana.ai for more details on what we've announced and what else is coming out today.

Introducing Assistant Workspace, a full-page surface for Grafana Assistant, built for the conversations that outgrow a sidebar. Dig into longer investigations, compare data side by side, and keep your train of thought in one place — then turn what you find into a dashboard without starting over. When a quick question becomes a real investigation, open it in Workspace and keep going. In this video, Ed Poole gives us a demo of how to use Workspace, including the use of canvases to see more information than before.