Operations | Monitoring | ITSM | DevOps | Cloud

What if you could counterspell an agent action? GitKraken Desktop 12.4 pulls the whole AI agent workflow into one place, so you stay in the flow. Back in 12.0 we shipped Agent Sessions, where you kick off AI coding agents right inside the context of your repo. GitKraken 12.4 builds on that. What's new in 12.4: This release is not about handing more of your work to agents. It's about seeing everything they do, and deciding what actually changes.

We spend thousands of dollars "token maxing" and running endless debugging cycles just to walk our LLMs through a problem. But is the AI actually failing, or are we just withholding the right environment? Giving your AI assistant its own sandbox to test hypotheses might just be the missing link in your development workflow.

Why Observability Systems Fail AI Code.

OpenTelemetry instrumentation used to mean hours of manual work, wiring up metrics service by service. Now you can just ask for it. Tell an AI agent what you're trying to observe, something like "add OpenTelemetry so I can track this application's performance," and it turns that into an intent specification, then enriches your existing code with instrumentation to match. OpenTelemetry is open source and on GitHub. Pairing it with an AI agent that actually understands your codebase is what turns "add some metrics" into instrumentation that's useful.

We’re back with another roadmap stream! You might think to yourself, “Talking about 2027 already? Isn’t that a bit early? I’m still sweating and lying out by the pool!” But planning this far ahead will give you plenty of time to sort out priorities, talk to relevant parties, set your budget(s), and more. Having these discussions in August may feel extreme but the leaves will fall and the snow will pile up before you know it, so you might as well get started now!