Introduction: The New Reality of Coding and Observability
The way engineers write code is evolving rapidly. Agentic tools like Cursor and Claude Code have become essential, handling many day-to-day tasks directly from the command line. This shift greatly accelerates code generation, but it also introduces a new challenge: context switching. When you have to jump from your terminal into a separate observability tool, the flow is broken. Moreover, agents themselves suffer from a visibility gap—they can see your local code but are blind to production behavior. They don’t know about a latency spike on checkout or whether your SLOs are being met. They generate code based on assumptions rather than actual system state.
To address these issues, Grafana has launched the public preview of gcx, the new Grafana Cloud CLI. gcx brings full observability—and the power of Grafana Assistant—directly into your terminal. This means you and your agents can spot and resolve incidents in minutes instead of hours, all without leaving your command-line environment.
From Greenfield to Full Observability in Minutes
Most services start out with no instrumentation, no alerts, and no SLOs. gcx treats this as a starting point, not a blocker. You simply point your agent at the service and ask it to bring the system up to standard. gcx exposes the necessary primitives across the full observability lifecycle.
Instrumentation: Wire OpenTelemetry from the Terminal
With gcx, you can instrument your codebase with OpenTelemetry directly from the command line. The tool validates that metrics, logs, and traces are flowing, and confirms data lands in the correct backends—all without leaving your terminal. This eliminates the need for manual configuration and speeds up the onboarding process.
Alerting, SLOs, and Synthetics
gcx lets you generate alert rules based on the signals your service actually emits. Define an SLO against real latency or availability indicators and push it live immediately. You can also stand up synthetic probes so users aren’t the first to report an outage. All of these operations are performed via CLI commands, making it trivial to automate and repeat.
Frontend, Backend, and Kubernetes Monitoring
Onboard a Faro-instrumented frontend by creating the app and managing sourcemaps (so stack traces remain readable). For backend services and Kubernetes infrastructure, use the Instrumentation Hub to quickly set up monitoring. gcx handles the complexity of wiring everything together.
Everything as Code: Git-Ops for Observability
One of gcx’s standout features is its commitment to “everything as code.” You can pull dashboards, alerts, SLOs, and checks as files. Edit them locally with your agent, version-control them, and push changes back. When a human needs to dive deeper, gcx opens a deep link directly into Grafana Cloud. This turns what used to be a multi-day ticket into a single agent session.
Why Agents Need Production Context
Without production context, an AI agent is merely pattern-matching on source files and hoping for the best. With gcx, the same agent can read the state of the running system—real metrics, logs, traces, and alerts—and make informed decisions based on what is actually happening. This closes the visibility gap and leads to more reliable, context-aware code generation.
Get Started with gcx Today
The public preview of gcx is available now. Whether you’re a solo developer or part of a team using agentic tools, gcx puts observability where you need it most: in the terminal. Learn how to instrument your service or explore the as-code workflow to see how gcx can transform your incident response.
Summary
gcx brings Grafana Cloud observability to the command line, empowering human engineers and AI agents alike. With instrumentation, alerting, SLOs, synthetics, frontend/backend monitoring, and a full as-code workflow, gcx slashes the time from problem detection to resolution. It’s the CLI tool that finally bridges the gap between coding and observing.