Operations | Monitoring | ITSM | DevOps | Cloud

The recent mystery around Ox Alpha last week and the week before was a fun slice of what makes social media fun. The hunt for the model provider and how people did that discovery should be studied. But, this post is more about stealth models in general. You might be wondering what the phrase “stealth model” even means and if you already know, you might still be curious about why companies release stealth models.

Giordano “Gyo” Piazza, GitKraken’s Director of Engineering, has spent the past month heads down on the next version of Kepler. When he got on a call to talk through it, he skipped the changelog and went straight to the part he actually wanted to talk about: how agents show their work.

Perplexity was a big name a few years ago. But, we haven’t heard much out of them lately. There are plenty of posts on social media criticizing Perplexity to that effect. One thing that the posts miss is that Perplexity is still the king of AI search. Google is giving it a run for its money with the AI previews on Google search, but Perplexity still wins out in several measurable ways.

Choosing a software engineering intelligence platform is one of those decisions that gets more complicated the longer you wait. The category has grown rapidly, and every vendor claims to track the metrics that matter. GitKraken Insights gives you a full-stack view of engineering performance, from DORA metrics to AI tool ROI, in a platform trusted by over 40 million developers. But it isn’t the only option on the market.

Your code review tool does more than display diffs. It shapes how your team shares knowledge, catches bugs, and ships software. With AI-generated code accelerating PR volume, choosing the right code review platform is a decision that directly affects your team’s velocity. GitKraken connects PR workflows, multi-repo management, and AI-assisted review into a single developer experience platform.

We hosted a live launch preview, “Level Up Your Agentic Workflow,” to introduce two things at once: GitKraken Insights for Developers and Kepler. Jeremy Castile, our VP of Developer Research, opened with research on how teams are actually using AI agents today. If you want the full breakdown of that data, including the adoption numbers and the gap between feeling faster and proving it, we published it separately in State of AI in Engineering 2026: The Proof Gap.

The biggest Kepler update since public preview is live. If you tried Kepler early, here’s what changed, and the problem it’s built to solve.

If you look at the people posting to social media the most about AI, you’ll probably feel left behind. They’re running dozens or hundreds of agents and probably shipping more than you. But, they are not representative of the rest of the dev world. They are the 1% of the 1%. The thing that might be missed is that you reading their posts is probably separating you from a much larger cohort of devs that are still trying to figure out how to use AI effectively in their day to day work.

What 554 developers and engineering leaders told us about AI, agents, and the measurement gap nobody’s closing. Ask a developer if AI made them faster this year, and 84% will say yes. Ask their VP to put a number on it for the board, and 39% will have nothing to show. That gap, not adoption, is the real story in engineering right now.

AI coding tools were supposed to mean developers work less. On a recent webinar recorded with LeadDev, senior engineering manager Vernon put words to something a lot of teams are quietly noticing instead: “It’s concerning because it’s the opposite of what was promised. We were supposed to be working less.”

Splitting one big pull request into five smaller ones doesn’t automatically make review faster. It just moves the complexity from the diff to your head, unless something keeps track of the order for you.

Most companies buy AI tools for developers and hope the impact shows up somewhere. A faster sprint. Fewer escaped bugs. Something. What they don’t have is a way to actually see it happening, which means adoption becomes a leap of faith instead of a measured bet. That’s the gap Kepler and GitKraken Insights close together, and it’s worth understanding as one story, not two separate product updates.

Visualize branches and commits, manage parallel work and agents, and run your entire Git workflow from one view. AI changed how code gets written. It also changed what developers spend their time doing. Today, developers are reviewing AI-generated changes, coordinating parallel work across branches and worktrees, cleaning up commit history, resolving conflicts, and getting everything ready to merge.

Most companies will tell you they’re customer-obsessed. Fewer can point to the actual mechanism. At GitKraken, it isn’t a quarterly survey or a roadmap council. It’s a Slack channel where developers vent about their Git workflow, and the desktop team is already in there reading it.

The secret sauce that powers Agentic Development Environments (ADEs) like Kepler is a little thing called the Agent Client Protocol (ACP). In this context, Kepler is the Client and harnesses like Claude Code and the Codex CLI are the Agents. We’re going to go over some of the details about how it works, how we use it at GitKraken, and how the protocol may be changing for the better.

Leadership has stopped asking whether your team is using AI. They’re asking what you’re delivering with it. That’s a harder question, because most of the numbers teams have been reporting, adoption rate, seats activated, prompts run, don’t actually answer it.

Adding a second AI agent to a project feels like doubling your output. In practice, it usually means doubling your bookkeeping too. Every agent needs its own worktree so it can work without touching the branch someone else, human or otherwise, is using. Multiply that by five agents across three repos, and the isolation that made parallel work possible starts generating its own kind of work: which worktree goes with which branch, which ones are stale, which upstream nobody remembers creating.

Most teams adopting AI agents are making a bet on which one wins. Claude or Codex, Copilot or something newer next quarter. That bet is the wrong one to make. The agent you use will keep changing. The workflow around it is what actually needs to hold up.

The frontier models have led the pack for a while now. It seems like the big players of Anthropic and OpenAI keep leapfrogging each other by a couple points in benchmark scores every other month. But, a trend we are starting to see is that open weight models are improving by leaps and bounds. They don’t hold the lead and probably won’t for a while, but the fact that open models are scaring the leaders is something to think about.

GitKraken Desktop 12.4 gives developers running several worktrees and AI agent sessions a single graph to see it all, plus an inline way to approve or deny what each agent wants to do. It ships August 4, 2026, with updates carried forward from 12.1 through 12.4.

Every so often we sit down with someone from our support team and turn their week into a blog post. First up: Roberto Vizcarra, on four things generating tickets lately, AI credits, student plans, integrations, and Mac performance. Here’s what changed and what to do about it.