Gain Production Insight from Your Terminal: The gcx CLI for You and Your AI Agents

Why Terminal-Native Observability Matters

Modern software development has shifted significantly. Engineers now spend most of their day in the command line, assisted by powerful agentic tools like Cursor and Claude Code that handle routine coding tasks with remarkable speed. While these tools accelerate code generation, they introduce a new problem: context switching. When an issue arises, developers must leave their terminal and jump into separate monitoring dashboards, breaking their flow and slowing down incident response.

More critically, AI agents that help write code are blind to production reality. They see your source files but have no awareness of a latency spike during checkout, whether your service meets its SLOs, or if an error rate just climbed. They generate code based on assumptions, not actual system behavior. This visibility gap means agents can inadvertently suggest changes that ignore real-world performance issues.

To close this gap, we have released the public preview of gcx, the Grafana Cloud CLI. gcx brings Grafana Cloud and the Grafana Assistant directly into your terminal—and into the agentic coding environment running inside it—enabling you to detect and resolve incidents in minutes rather than hours.

gcx: From Zero to Full Observability in Minutes

Most services start with no instrumentation, no alerts, and no SLOs. That is the normal starting point, and gcx treats it as an opportunity rather than a blocker. Simply point your agent at the service and ask it to bring observability up to standard. gcx exposes the essential primitives across the entire observability lifecycle:

Instrumentation Made Simple

Wire OpenTelemetry directly into your codebase from the terminal. Validate that metrics, logs, and traces are flowing correctly. Confirm that data lands in the appropriate backends—all without leaving the command line.

Alerting, SLOs, and Synthetic Checks

Generate alert rules based on the signals your service actually emits. Define a service level objective (SLO) against real latency or availability indicators and push it live. Set up synthetic probes to detect outages before your users do.

Frontend and Backend Observability

Onboard a Faro-instrumented frontend—create the app, manage sourcemaps so stack traces remain readable. Onboard backend services and Kubernetes infrastructure using the Instrumentation Hub. Whether you work on the client side or server side, gcx streamlines the setup.

Everything as Code

Pull dashboards, alerts, SLOs, and synthetic checks as files. Edit them locally with your agent, then push them back. When a human needs to investigate further, open a deep link directly into Grafana Cloud. What used to be a multi-day ticket becomes a single agent session.

Empowering AI Agents with Production Context

Accessing Grafana from the terminal is convenient, but the true power of gcx is revealed when you give your AI agents access to it. Without production context, an agent is essentially pattern-matching on source files and hoping to find the right answer. With gcx, the same agent can read the state of the running system—latency distributions, error rates, resource utilization—and make informed decisions based on actual behavior rather than speculation.

This transforms how agents assist you. Instead of suggesting code changes in a vacuum, they can check whether the proposed optimization will improve the observed bottleneck. They can automatically adjust alert thresholds when traffic patterns change. They can even initiate rollbacks or scaling actions based on real-time metrics, all from within your terminal workflow.

Get Started with gcx Public Preview

The gcx CLI is now available in public preview. Terminal-native observability reduces friction, accelerates incident response, and gives your AI agents the production awareness they need to be truly effective. Visit the Grafana Cloud documentation to install gcx and start bringing observability to your command line today.