Google Unveils Jules: A Revolutionary Autonomous AI Coding Assistant

Google releases its asynchronous Jules AI agent for coding - how to try it for free

The race to deploy AI agents is heating up. At its annual I/O developer conference yesterday, Google announced that Jules, its new AI coding assistant, is now available worldwide in public beta. The launch marks the company's latest effort to corner the burgeoning market for AI agents, widely regarded across Silicon Valley as essentially a more practical and profitable form of chatbot. Virtually every other major tech giant -- including Meta, OpenAI, and Amazon, just to name a few -- has launched its own agent product in recent months. (Disclosure: Ziff Davis, ZDNET's parent company, filed an April 2025 lawsuit against OpenAI, alleging it infringed Ziff Davis copyrights in training and operating its AI systems.) Also: I tested ChatGPT's Deep Research against Gemini, Perplexity, and Grok AI to see which is best Originally unveiled by Google Labs in December, Jules is positioned as a reliable, automated coding assistant that can manage a broad suite of time-consuming tasks on behalf of human users. The model is "asynchronous," which, in programming-speak, means it can start and work on tasks without having to wait for any single one of them to finish. Afterward, the model provides a full outline of the changes that were made to a user's code, providing clarity into its reasoning process. Jules is built upon Gemini 2.5 Pro, a large language model that Google debuted in March, describing it at the time as its "most advanced model for complex tasks." Gemini 2.5 Pro outscored other industry-leading models, including OpenAI's o3-mini and Anthropic's Claude 3.7 Sonnet, on key benchmarks like math and code editing. As such, Jules offers some advanced coding capabilities. It can work directly within a user's codebase, for example, absorbing a project's full context and making decisions without the need for a sandbox (that is, a separate and controlled testing environment). It also integrates directly with GitHub, eliminating the need for developers to manually switch back and forth between coding platforms. Also: Gemini Pro 2.5 is a stunningly capable coding assistant - and a big threat to ChatGPT "We're at a turning point: agentic development is shifting from prototype to product and quickly becoming central to how software gets built," Kathy Koravec, director of product management at Google Labs, wrote in a company blog post published yesterday. While Google has yet to officially clarify the inspiration behind the name for its new model, it could be a nod to the visionary science-fiction writer Jules Verne. Its logo, an octopus, could be a loose allusion to that author's 1870 novel Twenty Thousand Leagues Under the Sea, which features not an octopus but a giant squid. The logo was also likely chosen to symbolize the model's ability to manage multiple tasks at once, like the semiautonomous arms of an octopus. Jules is now available for free in public beta, with some usage limitations. You can give it a try here. Get the morning's top stories in your inbox each day with our Tech Today newsletter.

Google Jules : New Free Autonomous Coding Assistant for Developing Apps

What if the future of coding didn't just assist you -- but worked for you? Meet Jules, Google's bold answer to the limitations of today's coding assistants. Unlike tools like GitHub Copilot or OpenAI's Codex, Jules doesn't wait for your next input or suggestion. Instead, it operates autonomously, taking tasks from concept to completion without constant oversight. Imagine assigning a coding task, stepping away, and returning to find a polished pull request waiting in your GitHub repository -- complete with detailed documentation. Today, Jules is entering public beta, available to everyone. No waitlist. Worldwide, everywhere where the Gemini model is available. In this feature, Prompt Engineering explore how Jules is redefining the boundaries of autonomous coding agents, from its seamless GitHub integration to its ability to plan, execute, and document tasks independently. You'll discover how this tool goes beyond productivity boosts, offering real-time access to the latest coding standards and even audio summaries of project updates. But is Jules truly the "Codex killer" it's being hailed as, or does it come with limitations that developers must navigate carefully? By the end, you'll have a clearer picture of whether this innovation is a glimpse into the future of software engineering -- or a step too far. After all, when machines take the reins, what's left for us to do? Jules stands apart from traditional coding tools by functioning as an asynchronous agent, meaning it works independently without requiring constant input or supervision. Once you assign a task, Jules takes full control, crafting a detailed plan, executing it, and delivering the results. This autonomy allows developers to focus on more critical, high-priority tasks while Jules handles repetitive yet essential activities, such as: By automating these processes, Jules not only enhances productivity but also minimizes the risk of human error. This makes it an invaluable tool for developers seeking to streamline their workflows and maintain high-quality codebases. One of Jules' most notable features is its seamless integration with GitHub, a platform widely used for version control and collaboration. By connecting your GitHub account, you can assign tasks directly to Jules, which then generates pull requests complete with detailed explanations of the changes made. This functionality fosters better collaboration and ensures that all team members remain informed about project updates. For instance, whether you need to resolve bugs, refactor existing code, or implement new features, Jules simplifies the process by automating the creation of well-documented pull requests. This not only saves time but also ensures that every change is clearly communicated, reducing the potential for misunderstandings within development teams. Check out more relevant guides from our extensive collection on Autonomous Coding Agent that you might find useful. Jules excels in autonomous task planning and execution, which are central to its functionality. When you assign a task, Jules develops a structured plan and presents it for your approval. Once approved, it executes the task with precision and attention to detail. For example, if you request an update to project dependencies, Jules will: This meticulous approach ensures that the output aligns with your expectations while minimizing the risk of introducing errors into your codebase. By handling these tasks autonomously, Jules allows developers to allocate their time and energy to more complex and creative aspects of software development. Unlike many AI coding tools, Jules has internet access, allowing it to retrieve the latest documentation and resources. This capability ensures that the code it generates adheres to current standards and best practices. For example, if you assign a task involving a specific library, Jules can consult the library's documentation to ensure proper implementation. This feature not only saves time but also enhances the quality and reliability of the generated code. By staying up-to-date with the latest developments in programming languages, frameworks, and libraries, Jules helps developers maintain a modern and efficient codebase. Jules introduces an innovative feature called "Codecast," which provides audio summaries of recent repository activities. This feature is particularly useful for staying informed about changes, pull requests, and other developments without having to sift through detailed logs. For example, if your team has been working on multiple features simultaneously, the Codecast can deliver a concise overview, helping you make informed decisions more quickly and efficiently. This functionality is especially beneficial for team leaders or developers managing multiple projects, as it provides a quick and accessible way to stay updated on progress without interrupting their workflow. To ensure accessibility for developers of all levels, Jules offers a free tier that allows up to five tasks per day at no cost. This feature is particularly advantageous for individual developers or small teams who want to explore the potential of autonomous coding agents without committing to a paid plan. By providing this option, Google aims to provide widespread access to access to innovative AI tools, allowing a broader audience to experience the benefits of Jules. The free tier serves as an excellent starting point for developers looking to integrate AI into their workflows, offering a risk-free opportunity to evaluate its capabilities and impact on productivity. Jules represents a significant advancement in the evolution of autonomous coding agents, showcasing the growing role of AI in software engineering. By automating complex tasks and integrating seamlessly into existing workflows, Jules enables developers to focus on innovation and problem-solving. Its effectiveness, however, depends on your ability to assign clear, well-defined tasks and maintain strong programming fundamentals. As tools like Jules become more prevalent, developers will need to strike a balance between using AI for efficiency and adhering to best practices to ensure the long-term quality and sustainability of their projects. Jules is not just a tool for automation; it is a glimpse into the future of software development, where AI and human expertise work together to achieve greater heights in innovation and efficiency.

Google Releases Jules Coding Agent to Take on OpenAI Codex

It runs in Google Cloud's secure virtual machine and clones your codebase to process multiple requests in parallel. At the I/O 2025 event, Google released its Jules coding agent to all users worldwide. Jules is an autonomous coding agent that can read your codebase, understand your intent, and perform actions to get things done. It's an asynchronous coding agent that connects to your existing repository and clones the codebase into a secure Google Cloud virtual machine (VM). It means that the AI agent runs in the cloud, and not on your local machine. Just like OpenAI Codex, Google's Jules AI agent can write tests, build new features, fix bugs, and update dependency versions. In addition, it can also provide audio changelogs. You can assign tasks to the Jules coding agent, and it works in the background. When the task is completed, it shows its reasoning, plan, and a diff of the changes made. Google says your private codebase is not used for training AI models, and the data remains isolated in the secure environment. Google has also added parallel execution to Jules, which means you can assign multiple tasks simultaneously. Moreover, you can connect your GitHub repo to understand the full context of your existing project. Finally, Google says since Jules is in public beta, it's available free of charge, however, some usage limits do apply. You can access Jules via jules.google.com.