Operations | Monitoring | ITSM | DevOps | Cloud

Code Flow is what we call the shift happening across every engineering team right now: AI can generate code faster than ever, but that doesn't mean it ships any faster. In this clip from our Code Flow Live stream, our team unpack why adding AI coding agents to a team is a lot like adding lanes to a highway that's already jammed. More lanes, more cars, same traffic.

Everyone's betting on which AI agent wins. Wrong bet. The agent you use will keep changing. The workflow around it is what needs to hold up. That's why Kepler connects to any agent, Claude, Codex, Copilot, instead of locking you into one.

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.

Running Claude in one terminal and Cursor in another isn't a workflow. It's a juggling act. We talked to the engineer who got tired of it and built Kepler instead: one place to run agents, review PRs, and stay in control.

AI didn't just change how fast code gets written. It exposed a new bottleneck: everything around the code. Reviews slow down. Context gets lost. Planning drifts from implementation. Teams move fast and still feel stuck. That's the problem GitKraken is built to solve, and this Friday we're going live to walk through what's changed. We'll cover the latest Code Flow Company features we've shipped, how they connect developers, AI agents, and production into one system, and what it actually looks like to go from plan to main without the chaos.

New data from our VP of Dev Research on The Programming Podcast. 84% of devs feel more productive with AI coding tools 43% feel MUCH more productive The kicker: productivity feeling scales directly with how agentic your workflow is. The more agents do, the better it feels.

AI didn't just change how fast code gets written. It exposed a new bottleneck: everything around the code. Reviews slow down. Context gets lost. Planning drifts from implementation. Teams move fast and still feel stuck. That's the problem GitKraken is built to solve, and this Friday we're going live to walk through what's changed. We'll cover the latest Code Flow Company features we've shipped, how they connect developers, AI agents, and production into one system, and what it actually looks like to go from plan to main without the chaos.

New: launch a Claude Code or Codex CLI session straight from the Agents panel. One click → isolated worktree → setup commands run → agent starts. Your other worktrees don't even notice. Parallel AI agents without the chaos. That's code flow.

AI adoption is easy to report. Business impact is harder to prove. Engineering leaders are under pressure to show what AI is actually changing — not just who is using it, but whether it is improving delivery, quality, developer experience, and business outcomes. This discussion between 3 engineering leaders explores how to move beyond vanity metrics, build a practical measurement approach, and communicate AI’s value to executives and CFOs with more credibility and less hype.

GitKraken Desktop gives you a visual Git client and AI coding agent hub in the same window. Manage branches, PRs, and conflicts on the Commit Graph while running Claude Code, Copilot, Codex, or Gemini in separate worktrees. Available on Windows, Mac, and Linux.