Jules

When we launched Jules, it was an experiment to learn how asynchronous coding agents can help developers ship faster. Seeing what you built taught us so much about where agentic development is headed, directly shaping several products across @Google. We’re working on bringing our learnings from Jules into @antigravity so you get the best of both worlds: autonomous remote background task execution and an agent-first development environment. As we focus on this unified experience, Jules will be winding down. Whether you used Jules to crush bugs, write tests, or launch features— thank you for shaping the future of agentic coding! 💙🦑

What if your AI agents could read the room, read your product, and read you? The best agents won't be judged by how much code they write, but by how well they protect your focus. Because human context switching is costly, the future belongs to agents that understand full development context; and know when to stay silent. Read the full post: The future of agentic coding is focus Link: labs.google/code/experiments…

Coding agents are usually just reactive, waiting for us to tell them what to do. Yet the best collaborators don't wait to be asked. They notice. They anticipate. They surface the thing you needed to know before you even realized you should look. At Google Labs we are rethinking how to evaluate agents so it can act as a partner in your work. Check out our latest blog: Measuring What Matters with Jules developers.googleblog.com/me…

Waitlist - shorturl.at/FbAaZ

Jules works with the lid closed. Join the waitlist for the new Jules today. Link in comments.

Heads up! We're currently experiencing a surge in traffic and usage, which means you might notice Jules is responding a bit slower than usual today. Our team is actively working behind the scenes to expand capacity and prioritize your requests. Thank you for building with us. We’ll keep you updated!