Google appears to be building the next generation of its Jules coding agent, internally referenced as “Jitro,” which could represent a fundamental rethinking of how developers work with AI-powered software engineering tools. While the current Jules experiment has seen little visible progress in recent months, evidence points to a parallel effort focused on a completely new version that moves beyond the prompt-and-execute model that defines most coding agents today.
The upcoming experience, expected to launch under a waitlist, carries messaging that positions it as a generational leap. Rather than asking developers to manually instruct an agent on what to build or fix, Jules V2 appears designed around high-level goal-setting, think of KPI-driven development, where the agent autonomously identifies what needs to change in a codebase to move a metric in the right direction (* speculation).
Something new is coming...
Manually prompting your agents is so… 2025.
The Jules team has been working on something new for 2026.
Join the waitlist below to be the first to try it.
This would mark a departure from the task-level paradigm seen across competitors like GitHub Copilot, Cursor, and even OpenAI’s Codex agent, all of which still rely on developers defining specific work items. A dedicated workspace for the agent suggests Google envisions Jitro as a persistent collaborator rather than a one-shot tool.
Jitro tools 👀
- List the goals in the user's Jitro workspace.
- Get a single Jitro goal by its resource name
- List insights for the user's Jitro workspace.
- Get the update history for a specific insight.
- List the user's configured tool integrations (MCP remote servers, API integrations).
- List the tools available from one or more of the user's configured integrations.
- Create a new goal in the user's Jitro workspace after helping them articulate a high-quality goal.
- Create a specific, actionable task in the user's Jitro workspace.
The timing is notable. Google I/O 2026 kicks off May 19, and this is exactly the kind of showcase-ready feature Google would want to unveil alongside its broader Gemini ecosystem updates. Google has been steadily expanding its AI developer tooling through Gemini integrations in Android Studio, Firebase, and Cloud, and a goal-oriented coding agent would fit neatly into that strategy, particularly for enterprise teams that care more about outcomes than individual pull requests.
If Jules V2 ships as described, the primary beneficiaries would be engineering teams managing large codebases where incremental improvements compound, performance optimization, test coverage, and accessibility compliance. The risk, of course, is that autonomous goal-pursuing agents introduce unpredictable changes, and trust will be the key barrier to adoption. None of the UI is visible yet, so the full scope remains unclear, but the direction alone signals where Google thinks AI-assisted development is heading next.
