Google Rolls Out Jules, Its Asynchronous AI Coding Agent, to All Users After Successful Beta

Google has officially launched its AI-powered coding agent, Jules, into general availability after a successful beta testing phase that began in May 2025. Originally introduced as a Google Labs project in December 2024, Jules is designed to help users write, test, and improve code asynchronously.

Powered by Gemini 2.5 Pro—Google’s most advanced large language model—Jules can manage complex, multistep coding tasks with advanced reasoning and parallel processing.

"Jules now uses the advanced thinking capabilities of Gemini 2.5 Pro to develop coding plans, resulting in higher-quality code outputs," Google said in a blog post.

The company says Jules is not just for professional developers; it's also useful for those working on website design, automation, and app development, even without formal coding experience.

The updated version includes a streamlined UI, multimodal support for visual outputs, GitHub Issues integration, test result visualizations, and the ability to reuse past setups. During beta, developers submitted hundreds of thousands of tasks, generating over 140,000 publicly shared code improvements.

What sets Jules apart is its asynchronous operation. “Jules operates like an extra set of hands. You can basically kick off tasks to it, walk away, and come back later with the work completed,” Google Labs Director of Product Kathy Korevec said in an interview.

Jules is part of Google’s broader push into agentic AI, designed to perform actions beyond chat responses. Unlike other coding agents like Cursor or Windsurf that require real-time user interaction, Jules runs independently in a virtual machine.

While free users are limited to 15 tasks and three concurrent jobs daily, advanced capabilities require a Google AI Pro ($124.99/month) or Ultra ($199.99/month) subscription. Google also plans to use Jules internally to boost its own development workflows.