Grafana Labs delivers AI for observability and observability for AI: always-on agents to operate systems, and OpenTelemetry-native visibility into the agents you ship

Grafana Labs, the company behind the open agentic observability cloud,  announced new releases at ObservabilityCON 2026 that move Grafana Cloud towards agentic operations, including the general availability of Agent Observability with OpenTelemetry support and of Assistant Watchers, and previews of Grafana Pages and Grafana Managed Sandboxes.

As AI moves into production, teams face two connected challenges: using agents to operate their systems and understanding the behavior of the agents themselves. In the 2026 State of Observability Report, also released this week by Grafana Labs and ETR, a Futurum company, 68% of the 300 IT and engineering leaders surveyed have moved AI for observability past investigation into pilots or production. But confidence depends on the task and readiness varies: 85% report comfort with read-only investigation, compared to 52% for full autonomous remediation. Grafana Labs is building toward a platform with agents that act, allowing each organization to decide how much human oversight to retain based on its own level of trust and risk profile.

Teams also need to watch the agents they ship. Some 80% of surveyed organizations are building or operating LLM-powered features, yet 45% have pieced together AI observability from open source while only 25% run a purpose-built product. Today’s announcements cover both sides: AI for observability, so agents can investigate and act with people in control, and observability for AI, so teams can see and trust the agents they run.

AI for observability: The future of agentic operations

Grafana Assistant is the AI agent built into Grafana Cloud, where teams ask questions in plain language and get answers from their own telemetry. Assistant Investigations, generally available since late July, takes that further: it runs longer, deeper investigations that can start automatically from an alert or incident, and teams can run them from the platform, Slack, the Grafana Cloud MCP server, or gcx. Today’s releases extend that workflow:

• Assistant Watchers (GA): Watchers are always-on agents that help teams detect changes they have not captured in predefined alert rules. Teams describe what matters in plain language, and a Watcher learns normal patterns from their telemetry and surfaces findings when those patterns change. Each finding arrives with the evidence behind it and routes through your existing Grafana Alerting, and a critical finding can trigger an Investigation. Watchers complement threshold-based alerts by helping teams identify emerging issues.
• Grafana Managed Sandboxes (public preview): Managed Sandboxes give Grafana Assistant a controlled cloud environment to develop proposed fixes using repository code and live telemetry. Assistant can clone a repository, investigate the code in the context of production behavior, prepare a fix, and open a pull request for human review and approval.
• Grafana Pages (public preview): With Grafana Pages, teams can build visualizations beyond any fixed constraints, making them closer to an app than a dashboard. Existing visualization components still work, and Pages supplement them as the next evolution of Grafana.

“Teams want agents to take on more of the work, but they need evidence and control at each step,” said Mat Ryer, Senior Director of AI, Grafana Labs. “Watchers surface emerging problems, Investigations help diagnose them, and Managed Sandboxes prepare fixes for human review. Together they make Grafana Cloud more autonomous, bringing detection, diagnosis, and proposed action into one workflow, grounded in the team’s own telemetry.”

Research on Grafana Cloud’s existing AI tools points to the potential operational benefits. According to IDC’s white paper The Business Value of Grafana AI (September 2026, sponsored by Grafana Labs), customers using Grafana Cloud’s AI tools reduced mean time to resolution by 63% and spent 46% less of each on-call shift gathering context.

Customers describe the same shift in day-to-day terms. SailPoint, the identity security company, is using Grafana Assistant to do the work that used to take the most time: migrating telemetry and investigating incidents. “I can just ask Grafana a question, leave it in that tab, go do something else, get Slack, get some coffee, and come back to a full investigation,” said Juan Carlos Ramirez, Senior Staff DevOps Engineer, SailPoint. “It’s personally helped me find spikes in logs that before the Assistant that would’ve taken me maybe 15, 20 minutes down to maybe five, and that’s while I’m doing other things.”

Observability for AI: Understand the agents in production

Agents are now production workloads, and they need the same visibility as any other service. Teams need to see what their agents do, what they cost, and whether their behavior holds up over time, without adding a separate tool. That is what Grafana Cloud Agent Observability solves, and today we are extending it with OpenTelemetry support, so agent activity shows up on the same open standard as the rest of the stack.

• Agent Observability with OpenTelemetry support (GA): Agent Observability helps teams understand what their agents are doing and what it costs them. Now, with OpenTelemetry support, agent activity shows up the same way any other service does, on the open standard that 76% of organizations already invest in, according to Grafana Labs’ 2026 Observability Survey.