Operations | Monitoring | ITSM | DevOps | Cloud

Your coding agent can debug production issues now. Yes… Not just “help you debug.” Actually run the investigation… FOR YOU! In this new era of agentic development, speed matters. And in the old days (you know… last week or so) we used to investigate production bugs ourselves. Manually. Like humans. But for a lot of incidents, we don’t need to do all of that anymore.

With GitOps, you can roll back your cluster with git revert and explain each approved change through a commit log. Routing normal changes through Git and running an in-cluster agent that detects drift from the repository gives infrastructure changes the same review and rollback discipline as application code, and Git preserves their history. This guide covers the four GitOps principles, the pull-based reconciliation workflow, and the tools and practices you need to get started.

Coralogix APM has told you which service is behind the latency. From today, the new APM experience tells you what is behind the service: the release, the environment, or the query one layer down. It watches every service you run from the moment it appears, without anyone writing an alert. And everything you see on the screen, your AI agent can use too: in Olly, from the Coralogix CLI, or through MCP in your IDE. A latency chart shows that something got slow.

Every page view, click, and session your RUM SDK captures lands in Coralogix as a log event under the cx_rum subsystem — the raw data behind how people actually use your product. You can turn it into a shareable report without writing a single query. Just ask your coding agent. Your agent queries that data through the CX CLI and writes the report for you: describe what you want in plain English, get a formatted report back — without leaving the terminal.

Tuning guardrails can take time. To accelerate this, we combined the power of Claude Code, Coralogix Telemetry and the CX CLI, to build a loop that iterates on guardrails. To test our loop, we built a fictional chat interface for an iGaming operator, that took bets, gave odds on markets and more, but with a catch: this agent was not permitted to make predictions about where the market was going. With our goal in place, we got to work designing our loop.