Grafana Labs has launched six artificial intelligence tools for software development and operations. The products are now generally available through its Grafana Assistant offering.
The release includes Grafana Assistant Investigations, Grafana Assistant Workspace, Grafana Assistant Automations, the Grafana Cloud MCP server, gcx, and Grafana Agent Observability.
The launch comes as companies work out how to monitor AI systems and agents as they take on a bigger role in engineering. In its 2026 Observability Survey, Grafana Labs found that 92% of practitioners saw value in AI catching anomalies, while 57% said they were implementing observability for their own AI systems in some form.
The new products target different stages of the software lifecycle, from planning and coding to production monitoring and incident response. The broader goal is to bring observability earlier into development rather than limiting it to systems already running in production.
Mat Ryer, Senior Director of AI at Grafana Labs, outlined that shift in a statement announcing the launch.
"We used to treat observability as something you bolt on just before code reaches production," said Mat Ryer, Senior Director of AI at Grafana Labs. "That's changing. Now, Grafana Assistant can review your plans before you've written a line of code, add the instrumentation for you once you have, watch features as they land in production, and stay with you as you scale while dealing with the inevitable incidents that follow. It's the same assistant end-to-end, and it doesn't just advise; it acts."
Planning tools
Grafana Assistant Workspace gives teams a shared space for chat history, a live canvas, and investigation reports. Grafana said the tool can be used before a service is built, letting engineers bring in an architecture and identify where it may not scale.
Workspace is paired with Grafana Assistant Investigations, which can turn an ongoing investigation into a report. Grafana positions that as a way to keep analysis and documentation in the same workflow.
Development stage
For development teams, Grafana Assistant can help instrument a new service by opening a pull request, setting up a data source, configuring Grafana, and checking whether telemetry is arriving. Two of the generally available products support that work: gcx and the Grafana Cloud MCP server.
gcx is a command-line tool for managing dashboards, alert rules, and data sources as code across self-managed Grafana deployments and Grafana Cloud. It is designed to work with coding tools such as Claude Code, GitHub Copilot, and Cursor, and also supports Git-based version control for dashboards and alerts.
One early user described how the approach fits into day-to-day engineering work.
"Root cause analysis and dashboard creations are prompts in the Grafana Assistant side-panel that help us understand anomalies and correlations across signals that lead to speeding things up," said Oren Lion, Director of Software Engineering at TeleTracking. "Now, with gcx, anyone can use Grafana Assistant in their coding agent, for example, to investigate flapping alerts, that's democratizing...Grafana!"
The Grafana Cloud MCP server is intended to give compatible clients direct access to a Grafana instance's dashboards, incidents, alert rules, and data sources. That allows engineers to query live telemetry from the environment where code is being written instead of copying information into separate chat tools.
Production use
On the operations side, Grafana Assistant Investigations and Grafana Assistant Automations are aimed at teams managing live systems and recurring checks. Engineers can ask questions about telemetry in plain language, while the system forms and tests hypotheses about what may have gone wrong during an incident.
Automations lets saved prompts run again on demand or on a schedule. Grafana gave the example of a daily error-rate summary being sent automatically to a Slack channel.
Rob Kacic, Engineering Manager at MasterControl, said the investigation tool had reduced the time needed for some troubleshooting tasks.
"When I'm in Grafana, it's never a leisurely thing. It's always under pressure; trying to find answers to unexpected issues in a very reactive situation," said Rob Kacic, Engineering Manager at MasterControl. "Grafana Assistant Investigations has been super helpful with that. I've had cases where it cut my time drastically; correlating backend errors and traces to specific front-end page IDs would have taken me hours, but with Grafana Assistant Investigations, it was a 15-minute task. Lowering that bar to entry has been the biggest win so far."
Monitoring AI
The sixth product, Grafana Agent Observability, focuses on monitoring AI systems themselves. It extends Grafana's OpenTelemetry-based monitoring to AI agents and tracks standard operational data such as usage, latency, and errors, alongside token use, cost, and conversation records.
According to Grafana, the product grew out of its own need to monitor Grafana Assistant as adoption increased. It also includes evaluators designed to inspect samples of conversations and identify issues such as hallucinations, drift, or policy violations.
An Alter Domus spokesperson said the tool had improved visibility into why AI-related systems were failing and where users were struggling.
"After two days in production [with Grafana Agent Observability], the difference was amazing," said a spokesperson for Alter Domus. "We started collecting information about our MCP servers, prompts, and conversations, so now we can understand why MCP servers fail and why users are not achieving what they expect when interacting with those systems."
Ryer said the six-product release reflected pressure on engineering teams to keep operational controls in step with AI-driven software delivery. "AI should allow you to move at 10x velocity, not produce incidents at 10x the rate," he said. "That's why we're releasing all these AI capabilities in a single week. Engineers shouldn't have to wait for their tools to catch up to how quickly they're already moving."