Google's AI Coding Agent Jules Exits Beta with Enhanced Features and Tiered Pricing

Google's AI coding agent Jules is now out of beta | TechCrunch

Google on Wednesday launched its AI coding agent, Jules, out of beta, just over two months after its public preview debut in May. Powered by Gemini 2.5 Pro, Jules is an asynchronous, agent-based coding tool that integrates with GitHub, clones codebases into Google Cloud virtual machines, and uses AI to fix or update code while developers focus on other tasks. Google initially announced Jules as a Google Labs project in December and made it available to beta testers through a public preview at its I/O developer conference. Kathy Korevec, director of product at Google Labs, told TechCrunch that the tool's improved stability drove the decision to take it out of beta after receiving hundreds of UI and quality updates during its beta phase. "The trajectory of where we're going gives us a lot of confidence that Jules is around and going to be around for the long haul," she said. With the wider rollout, Google introduced structured pricing tiers for Jules, starting with an "introductory access" free plan capped at 15 individual daily tasks and three concurrent ones, down from the 60-task limit during beta. Jules' paid tiers are part of the Google AI Pro and Ultra plans, which are priced at $19.99 and $124.99 a month, and offer subscribers 5× and 20× higher limits, respectively. Korevec noted that Jules' packaging and pricing are based on "real usage" insights gathered over the past couple of months. "The 60-task cap helped us study how developers use Jules and gave us the information we needed to design the new packaging," she said. "The 15/day is designed to give people a sense of whether Jules will work for them on real project tasks." Google also updated Jules' privacy policy to be more explicit about how it trains AI. If a repository is public, its data may be used for training, but if it is private, Korevec said that no data is sent. "We got a little bit of feedback from users that it [the privacy policy] wasn't as clear as we thought it was, and so we're most of it is just responding to that. We didn't change anything about what we're doing on the training side, but we changed the language," Korevec said. During the beta, Google said that thousands of developers tackled tens of thousands of tasks, resulting in over 140,000 code improvements shared publicly. Initial feedback led the Google Labs team to add new capabilities, including reusing previous setups for faster task execution, integrating with GitHub issues, and supporting multimodal input. The two primary users of Jules so far are the AI enthusiasts and professional developers, Korevec said. By running asynchronously in a virtual machine, Jules stands apart from top AI coding tools like Cursor, Windsurf, and Lovable, which all work synchronously and require users to watch the output after each prompt. "Jules operates like an extra set of hands... you can basically kick off tasks to it, and then you could close your computer and walk away from it if you want and then come back hours later. Jules would have those tasks done for you, versus if you were doing that with a local agent or using a synchronous agent, you would be bound to that session," Korevec explained. This week, Jules received a deeper integration with GitHub to open pull requests automatically -- just like it could open branches -- and a feature called Environment Snapshots to save dependencies and install scripts as a snapshot for faster, more consistent task execution. Since entering public beta, Jules has logged 2.28 million visits worldwide, 45% of them from mobile devices, per data from market intelligence provider SimilarWeb, reviewed by TechCrunch. India was the top market for traffic, followed by the U.S. and Vietnam. Google did not share specifics on Jules' user base and its top geographies. Korevec told TechCrunch that during the beta, the team observed that many people used Jules from traditional vibe coding tools to either fix bugs that might have been implemented or extend the vibe-coded project to make it more production-ready. Originally, Jules required users to have an existing codebase. But Google soon realized many potential users -- like those trying other AI tools -- might want to explore it without one. Korevec said the company quickly enabled Jules to work even with an empty repository. That helped increase its scope and usage. Google Labs' team also noticed an increasing number of users accessing Jules through their mobile devices. Although the tool does not have a dedicated mobile app, Korevec said users were accessing it through its web app. "Since it's a big use case that we're seeing emerging, we're absolutely exploring what the features are that people need on mobile a lot more," she noted. Alongside beta testers, Korevec stated that Google already uses Jules to help develop some projects internally, and there is now a "big push" to use the tool on "a lot more projects" at the company.

Google's Jules AI coding tool exits beta with serious upgrades - and more free tasks

Google's coding AI Jules is out of beta. Announced in a blog post on Wednesday, the coding helper will be powered by Google's Gemini 2.5 Pro LLM. You might recall that Google also recently announced its Gemini CLI GitHub Actions coding tool. What do all these developments mean? Let's unpack the announcements. Jules and Gemini CLI GitHub Actions are different beasts. Jules is meant for big projects, significant changes, and project planning. Also: Google embeds AI agents deep into its data stack - here's what they can do for you Gemini CLI GitHub Actions augments GitHub's workflow tool, GitHub Actions. The Gemini CLI version interacts with GitHub, helps respond to issues (problem reports), generates and responds to pull requests (submitted changes), and collaborates with other coders working on the same project. Here's a handy table that helps show the differences between the assistants: When I first tried Jules, it was the first day it became available as a beta offering. Although the assistant had some early server and availability problems, I was still able to add a new feature to my open-source project. I then deployed that new feature to all my users. That was on May 27. Since I didn't suddenly have 20,000 angry users screaming at me that I broke their sites (yes, I've done that before), it's pretty clear that the Jules additions worked well. Also: Google's Jules AI coding agent built a new feature I could actually ship - while I made coffee What I wanted to like about Jules is that it produces a plan of action in response to your prompt. You can (in theory) interact with Jules to refine that plan of action before it goes off and makes changes to your code. And when I first tried the tool, Jules did produce a plan of action. But like my little Yorkie pup, it didn't possess the patience to wait for me to say it was okay to go. This issue leads to small dogs trying to climb into your dinner dish, and big AIs that blast through an entire codebase in minutes. Fortunately, Jules branches your codebase. This feature ensures nothing is incorporated into your main release until after you approve it, as you would any other proposed change on GitHub. As of August 6, Jules is officially out of beta. The official release has what Google called a "new, more user-friendly interface." Jules also allows developers to reuse previous setups. This could be quite valuable because having to train the AI on your code for every coding request can substantially slow the process down and potentially introduce errors. This way, once you have a working prompt foundation, you can reuse it. Also: Gemini Pro 2.5 is a stunningly capable coding assistant - and a big threat to ChatGPT Jules also now has multimodal support. Google said: "Jules can test your web application and show you a visual representation of the results. This can help Jules iterate until it gets things right and gives you confidence in the code Jules creates." When I tested Gemini 2.5 Pro against my coding test suite, it did astonishingly well. Earlier versions of Gemini and its predecessor, Bard, did not perform nearly as well. Gemini 2.5 prioritizes speed and efficiency. In other words, it costs Google less to run each prompt. Google Gemini 2.5 Pro is intended for deep reasoning, accuracy, and handling complex tasks. Google prices Gemini 2.5 Pro at about 8 1/2 times the cost of Gemini 2.5, so we can pretty much assume Gemini 2.5 Pro uses a lot more resources for each query. As you read about this announcement, you might find some confusion. Based on the blog post, it's not fully clear whether Jules is powered by Gemini 2.5 or a combination of Gemini 2.5 and Gemini 2.5 Pro. According to Google's blog post announcing the public availability of Jules, the tool is "powered by Gemini 2.5." But later in the blog post, Google said: "Jules now uses the advanced thinking capabilities of Gemini 2.5 Pro to develop coding plans." I asked Google's team about the discrepancy. It confirmed to ZDNET that Jules uses the much more powerful reasoning model to plan out actions, and then executes those actions, also with the Gemini 2.5 Pro LLM. Given how impressive my testing was with 2.5 Pro, that's a good thing. Also: Claude Code makes it easy to trigger a code check now with this simple command Jules is offered in three pricing tiers. There are different limits for each pricing tier. When I tried Jules back in May, I was only given five tasks per day. I was able to make a feature addition to my project in just two tasks. You could still get quite a bit done even then. As of now, the free version of Jules allows 15 tasks per day, which is good. If you take the time to craft clear prompts, you're unlikely to need a lot more than that number each day. However, if you want more, you can move to Google's $20/month Pro plan or $250/month Ultra plan. Also: The best AI for coding in 2025 (including a new winner - and what not to use) Stay tuned. I plan to use the release version of Jules on another coding modification. I'll report back on my experiences. Did you try Jules during the beta? How does it compare to other AI coding assistants you've used? Do you see value in its planning-based approach, or do you prefer a more hands-on coding helper? And what do you make of the apparent confusion over which Gemini model the assistant uses? Let us know in the comments below.

Google's new tool wants to do your coding for you, and it's out of beta now

I've been testing nearly every AI tool since the boom began, and if there's one tech giant that's absolutely killing the game right now, it's Google. At this point, I'd argue it's leading the pack. Google's AI-powered personalized research assistant, NotebookLM, needs no introduction at this point and is simply one of the best productivity tools out there. But NotebookLM is far from the only AI tool that Google has been quietly working on. It's been testing and playing around with different AI tools in Google Labs, which is the company's experimental playground where it rolls out early versions of its most ambitious ideas for users to try before they go mainstream. One of these AI tools is Google's first coding agent, which has been under public beta since May. Today, the coding agent is officially graduating out of beta, and it's ready to take on your coding tasks. Google's AI coding agent, Jules, is officially available for everyone Today, Google Labs announced that its asynchronous coding agent, Jules, is finally available for everyone. The AI coding agent is powered by Gemini 2.5, the same model that powers the rest of Google's AI tools, including NotebookLM. Using Jules' "advanced thinking capabilities," the AI coding agent can come up with in-depth coding plans, ultimately leading to high-quality code outputs. What makes Jules unique from the many AI coding tools out there is the fact that it can run multiple tasks in parallel. I'm currently majoring in computer science, and if there's one thing that stands out to me, it's how Jules approaches coding more like a team of engineers than a single assistant. You can assign it multiple tasks, and it'll work through them simultaneously. One of the key parts of a tool being tested in beta is for the team to get feedback and figure out what's working, what's not, and what needs to be completely rethought. That's exactly what happened with Jules. The version of Jules we're getting today features a refreshed user-friendly interface, and also allows developers to reuse previous setups to allow new tasks to run a lot faster. Jules also comes with multimodal support now, meaning it can test your web applications for you and also show you a visual preview of what you're working on. Finally, Google is also announcing new structured tiers for Jules, which come with higher limits for Google AI Pro and Ultra subscribers. Google AI Pro subscribers now get 5x higher limits, and Google AI Ultra users get 20x higher limits. As a computer science student, I couldn't be more excited to see Jules finally out of beta, and I'm looking forward to putting it through its paces on real projects, both for uni and beyond.

Google's powerful AI coding agent Jules is now available to everyone -- here's why it's not just for developers

Google's AI-powered coding agent, Jules, is now available to the public. After a months-long beta, the asynchronous agent, designed to help users write, test and improve code, has launched with a slew of upgrades and broader availability. While it's clearly built with developers in mind, Google is also positioning Jules as a helpful tool for anyone dabbling in automation, app building or website design, even if they don't have a formal programming background. Jules runs on Gemini 2.5 Pro, Google's latest AI model optimized for logical reasoning and advanced planning. Jules has the ability to run tasks in parallel, making it especially efficient for large or multi-step workflows. The agent can now reuse past setups, visualize test results and even integrate with GitHub Issues for a more seamless development loop. During its beta, users submitted tens of thousands of taskss, resulting in over 140,000 code improvements shared publicly. Based on that feedback, Google has revamped the interface, fixed bugs and added features like multimodal support, allowing Jules to display visual outputs from web applications so users can see exactly what's happening with their code. But you don't need to be a full-time engineer to benefit. Casual users can now explore Jules through an introductory tier, ideal for side projects or early experimentation. For professionals, Google is offering Pro and Ultra tiers with significantly higher usage limits, up to 20x more capacity for enterprise or multi-agent workflows. This public release aligns with Google's broader push to make Gemini-based agents more accessible across all its products, not just in developer tools. The company is betting big on asynchronous, task-oriented AI that does more than just respond in a chat window, but executes as well. As AI assistants become more agentic, meaning they can plan, take action and adapt over time, tools like Jules may soon become essential to us beyond software development. We may seem them more often in business operations, creative work and even personal productivity. Jules is now available via Google Labs. Users with a Google account can try it for free, with upgrade options available through Google AI Pro and Ultra subscriptions.

Google has a new AI coding agent - and it's now free for everyone to use

Jules offers a free tier and two paid options with higher limits Google has announced the general availability of its latest AI coding agent, Jules. Initially revealed in December 2024 as a Google Labs project, Jules has now launched as an offering to paying customers, but limited free access is also confirmed. In a blog post announcing the launch, Google stated its decision to use Gemini 2.5 Pro would lead to "higher-quality code outputs." Designed for asynchronous operation, Jules can work in the background without user supervision, making it a considerable improvement over previous generative AI examples of coding assistants. Supporting multimodal inputs and outputs, Jules promises to write, test and improve code while simultaneously visualizing results for its users. Google hopes its new AI agent will not only be a valuable tool for developers, but also website designers and enterprise workers who don't have sufficient coding experience. During the beta phase, users already used Jules to submit hundreds of thousands of tasks, with more than 140,000 code improvements shared publicly. Now that Google's confident Jules works, general availability lands with a new streamlined user interface, new capabilities based on user feedback and bug fixes. Although the free plan gets the same Gemini 2.5 Pro backing as the higher-tier options, it's limited to 15 daily tasks and three concurrent tasks. Pro ($124.99/month) adds support for up to 100 daily tasks and 15 concurrent tasks, as well as "higher access to the latest models, starting with Gemini 2.5 Pro," suggesting it is likely to get model improvements before the free tier. Ultra ($199.99/month) gets priority access to those latest models, plus 300 daily tasks and 60 concurrent tasks.

Jules, our asynchronous coding agent, is now available for everyone.

Jules is officially out of beta and launching publicly, powered by Gemini 2.5. During the beta, thousands of developers tackled tens of thousands of tasks, resulting in over 140,000 code improvements shared publicly. Thanks to developer feedback, we've polished the user interface, fixed hundreds of bugs and launched new capabilities including reusing previous setups so new tasks run faster, GitHub issues integration and multimodal support. Jules now uses the advanced thinking capabilities of Gemini 2.5 Pro to develop coding plans, resulting in higher-quality code outputs. We're also introducing new structured tiers for Jules, including higher limits* for Google AI Pro and Ultra subscribers: These changes will begin rolling out today to Google AI Pro and Ultra subscribers. This includes eligible college students who can sign up for a free year of AI Pro. Get started today at jules.google.

Google makes Jules, its AI coding agent, available to everyone with free and paid plans - SiliconANGLE

Google makes Jules, its AI coding agent, available to everyone with free and paid plans Google LLC said today it's launching its artificial intelligence coding agent Jules in general availability, following a successful, months-long beta testing phase. An asynchronous agent, its purpose is to help users write, test and improve software code. The company first revealed Jules in December 2024 as a Google Labs project, before launching it in beta in May, shortly after it was showcased at Google I/O 2025. Now, after three months of extensive testing from developers and AI enthusiasts, it's finally being made available to paying customers. While Jules is clearly aimed at developers, Google also thinks it can be helpful for anyone who's dabbling in things like website design, app building or automation, and believes it can be especially powerful for enterprise workers, even if they lack formal coding skills. Google said Jules is powered by Gemini 2.5 Pro, which is the company's most advanced and sophisticated large language model, optimized for tasks that require reasoning and advanced planning. It has the ability to handle multiple tasks at once, in parallel, making it ideal for multistep workflows, the company said. It has also been updated, with a more streamlined user interface and new features such as multimodal support, allowing it to display visual outputs from web applications. In addition, Jules can now reuse past setups, visualize test results and integrate GitHub Issues, creating a more seamless development loop. According to Google, beta testers submitted hundreds of thousands of tasks to Jules, with more than 140,000 code improvements being shared publicly. In an interview with TechCrunch, Google Labs Director of Product Kathy Korevec said Jules runs asynchronously in a virtual machine, setting it apart from other popular AI coding agents, such as Cursor, Lovable and Windsurf. In contrast, those coding agents all work synchronously, which means that users have to be more involved, watching the output they generate after each prompt. "Jules operates like an extra set of hands. You can basically kick off tasks to it, and then you could close your computer and walk away from it if you want and then come back hours later," Korevec explained. "Jules would have those tasks done for you, versus if you were doing that with a local agent or using a synchronous agent, you would be bound to that session." Jules is not the only AI coding tool Google has built. The Gemini app possesses programming skills, and the company recently launched a new vibe-coding app called Opal. But unlike those apps, Google is actually planning to use Jules internally to help with its own projects. Korevec said the company has already tested it on some internal coding tasks, and is now making a "big push" to use it in "a lot more projects." While Google's staffers will presumably have unlimited access to Jules, everyone else will have to pay up if they want to go beyond the 15 individual daily tasks and three concurrent tasks allowed with the free version. To increase the number of tasks, users are required to pay for a Google AI Pro or Ultra subscription, which cost $124.99 and $199.99 per month, respectively. The launch of Jules is part of a broader push by Google to integrate its Gemini-based AI agents with all of its products, beyond developer tools. With its task-oriented agents, Google is betting that AI can be far more productive than just responding in a chat window, automating various aspects of work. AI agents can plan, take actions and learn over time, and they have the potential to enhance productivity in almost every aspect of business operations, and perhaps even assist in our personal lives, too.

Google's AI coding agent moves out of the testing phase

Powered by Gemini 2.5, the technology which debuted among testers in May, has left the beta stage. Google has officially launched Jules, its AI coding agent, which has been at the beta phase since May of this year. Powered by Gemini 2.5 Pro, the model was 'taught' by thousands of developers who addressed tens of thousands of tasks, resulting in the public sharing of more than 140,000 code improvements. The AI assistant can integrate itself with GitHub and other existing data storage technology, cloning your codebase into a secure Google Cloud Virtual machine. It can be used to perform tasks such as writing tests, feature building, providing audio changelogs and fixing bugs. According to Google, "Jules operates asynchronously, allowing you to focus on other tasks while it works in the background. Upon completion, it presents its plan, reasoning and a diff of the changes made. Jules is private by default, it doesn't train on your private code and your data stays isolated within the execution environment." Amid the wider launch, Google has introduced a structured, pricing tier system, starting with introductory access, a free plan that would allow a user to work on 15 individual tasks daily and three concurrent projects. Paid subscriptions include Google AI Pro and Ultra for people who have more intensive requirements. Agentic AI is the core focus for a number of key industry players in the technology space currently. With the power to autonomously work towards organisational ambitions and targets, with less human involvement, many companies are looking to AI-powered assistants to tackle complex and mundane tasks. In July of this year, French technology services company Capgemini acquired US company WNS for $3.3bn. The business explained, through the acquisition it aims to create "a leader in intelligent operations to capture enterprise investment in agentic AI to transform their end-to-end business processes". OpenAI also recently launched a new agentic AI feature, that reportedly has the ability to think and act proactively, via its own computer. The company stated that the new technology would give users far more power and control in the handling of tasks. However, it also introduced the idea that being novel and future-focused places the tech in a high risk category and that as a result, it must be used alongside a range of advanced safety features and regulatory policies. Don't miss out on the knowledge you need to succeed. Sign up for the Daily Brief, Silicon Republic's digest of need-to-know sci-tech news.

Google launches Jules AI coding agent out of beta

Google launched Jules, its AI coding agent, out of beta on Wednesday, approximately two months after its public preview debut in May. Powered by Gemini 2.5 Pro, Jules is an asynchronous, agent-based coding tool that integrates with GitHub, clones codebases into Google Cloud virtual machines, and utilizes AI to address or update code, allowing developers to allocate focus to other tasks. Google initially introduced Jules as a Google Labs project in December. The tool became available to beta testers through a public preview at the Google I/O developer conference. According to a recent TechCrunch article, Kathy Korevec, director of product at Google Labs, stated that enhanced stability influenced the decision to transition Jules out of beta. The tool received hundreds of user interface and quality updates during its beta phase. Korevec affirmed, "The trajectory of where we're going gives us a lot of confidence that Jules is around and going to be around for the long haul." With the wider rollout, Google implemented structured pricing tiers for Jules. An "introductory access" free plan is available, limited to 15 individual daily tasks and three concurrent tasks. This represents a reduction from the 60-task limit imposed during the beta phase. Jules' paid tiers are incorporated into the Google AI Pro and Ultra plans. The Pro plan is priced at $19.99 per month, offering subscribers five times higher task limits. The Ultra plan costs $124.99 per month and provides 20 times higher limits compared to the free plan. Korevec explained that Jules' packaging and pricing structure are based on "real usage" insights collected over the past several months. She further elaborated, "The 60-task cap helped us study how developers use Jules and gave us the information we needed to design the new packaging. The 15/day is designed to give people a sense of whether Jules will work for them on real project tasks." Video: Google Google also revised Jules' privacy policy to provide more explicit details regarding AI training data usage. Korevec clarified that if a repository is public, its data may be utilized for training purposes. Conversely, if a repository is private, no data is transmitted. "We got a little bit of feedback from users that it [the privacy policy] wasn't as clear as we thought it was, and so most of it is just responding to that. We didn't change anything about what we're doing on the training side, but we changed the language," Korevec stated. During the beta phase, thousands of developers engaged with Jules, tackling tens of thousands of tasks. This engagement resulted in over 140,000 code improvements that were shared publicly. Initial feedback from beta testers prompted the Google Labs team to implement several new capabilities. These additions include the ability to reuse previous setups, which facilitates faster task execution. Integration with GitHub issues was also introduced. Furthermore, Jules gained support for multimodal input, enhancing its versatility. Korevec identified two primary user groups for Jules during the beta: AI enthusiasts and professional developers. Jules distinguishes itself from other AI coding tools such as Cursor, Windsurf, and Lovable through its asynchronous operation within a virtual machine. These other tools operate synchronously, requiring users to monitor output after each prompt. Korevec elaborated on Jules' operational model: "Jules operates like an extra set of hands... you can basically kick off tasks to it, and then you could close your computer and walk away from it if you want and then come back hours later. Jules would have those tasks done for you, versus if you were doing that with a local agent or using a synchronous agent, you would be bound to that session." This week, Jules received an enhanced integration with GitHub, enabling the automatic opening of pull requests, mirroring its existing capability to open branches. A new feature called Environment Snapshots was also introduced. This feature allows users to save dependencies and install scripts as a snapshot. The purpose of Environment Snapshots is to facilitate faster and more consistent task execution by preserving specific environmental configurations. Insights gathered from beta trials informed Jules' development, spanning from "vibe coding" applications to mobile usage. Data from market intelligence provider SimilarWeb indicates that Jules recorded 2.28 million visits worldwide during its public beta period. Of these visits, 45% originated from mobile devices. India constituted the largest market for traffic, followed by the United States and Vietnam. Google did not disclose specific details regarding Jules' overall user base or its top geographies beyond this data. Korevec reported that during the beta, the development team observed many users transitioning from traditional "vibe-coding tools" to Jules. These users frequently employed Jules either to rectify bugs that had been introduced or to expand "vibe-coded" projects, making them more suitable for production environments. Initially, Jules necessitated an existing codebase for operation. However, Google recognized that many potential users, particularly those experimenting with other AI tools, might prefer to explore Jules without an immediate need for an established codebase. Korevec stated that Google quickly enabled Jules to function even with an empty repository, which broadened its scope and increased its utilization. The Google Labs team also noted a growing trend of users accessing Jules via their mobile devices. Although Jules does not currently feature a dedicated mobile application, Korevec confirmed that users were accessing the tool through its web application. "Since it's a big use case that we're seeing emerging, we're absolutely exploring what the features are that people need on mobile a lot more," Korevec affirmed. In addition to beta testers, Korevec confirmed that Google is already utilizing Jules internally to assist in the development of certain projects. There is a significant push to implement the tool on a greater number of internal projects within the company.

Google's Jules coding AI agent enters free beta: Here's what it can do

For the past few years, AI has been learning to code. Now it's ready to collaborate. With the launch of Jules, Google's first agentic coding assistant, developers finally have an AI teammate that doesn't just autocomplete a line, but actually takes on full-blown tasks, works in the background, and reports back like a junior engineer with discipline. And now, it's free for anyone to try. This isn't your average Copilot-style suggestion engine. Jules is Google's entry into the AI agent race, a smarter, more autonomous kind of assistant that operates independently inside your codebase, doing everything from bug fixing to feature building while you grab a coffee (or tackle more complex parts of your project). If traditional coding assistants were calculators, Jules wants to be your cloud-powered collaborator. Also read: Google Jules AI: The Autonomous AI Coding Assistant Changing Developer Workflows At its core, Jules is powered by Gemini 2.5 Pro, one of Google's most advanced AI models, capable of handling multi-step reasoning, large codebases, and multi-modal input. What sets it apart isn't just the brainpower, but the workflow. Instead of operating like a chat window, Jules clones your repo into a secure Google Cloud environment, analyzes the entire project structure, and runs in a sandboxed VM. You don't have to watch it think - you assign tasks, it plans out a solution, and gets to work. Imagine writing "Add unit tests for the payment API" or "Refactor the legacy CSS to Tailwind" and Jules simply does it. It reviews your repo, maps out a multi-step plan, and starts executing, pushing code changes via branches and even opening pull requests. It's like hiring a remote contractor who happens to be made of silicon. It's surprisingly capable. Jules can write unit and integration tests, fix bugs (even those spanning multiple files), update outdated dependencies, refactor legacy code, write and read from GitHub Issues. The entire thing is deeply GitHub-integrated, branches, issues, and PRs are first-class citizens in Jules' workflow. And it doesn't execute changes blindly. Before it starts, Jules presents a plan. You can review it, tweak it, or cancel it. Once approved, it runs the code in its VM, generates a diff, and waits for your nod to push. Also read: Google's Guided Learning versus ChatGPT's Study Mode: Which is better? It also runs multiple tasks in parallel, meaning you can have one agent fixing test coverage while another one modernizes your frontend. It's like having an AI development team that doesn't need coffee breaks but still waits for your sign-off. Google's clearly learned from past backlash. Jules doesn't train on private code. Public repositories are only used for training if permitted. Private code stays private, and the entire operation is cloud-contained. The privacy angle is important. This isn't some black box AI running in the cloud and hoovering your code for future model tuning. It's a personal agent, isolated, reviewable, and, crucially, not spooky. The free beta tier of Jules includes 15 tasks per day and allows up to three of them to run simultaneously. That's more than enough for most indie developers or small teams to experience what agentic coding feels like. If you want more horsepower, the paid tiers scale up: AI Pro ($19.99/month) unlocks up to 5x the daily tasks and AI Ultra ($124.99/month) gives you enterprise-scale execution with 20x the limits. Students also get a free year of AI Pro, a nice move to seed Jules into the next generation of developers. Well, yes and no. During the beta, developers found Jules impressive but not infallible. Some tasks are completed flawlessly, especially test generation or dependency updates. Others, especially more ambiguous bug fixes, can be hit or miss. Execution speed isn't always instant, and occasional plan failures still occur. But that's the nature of agentic AI, it's not just a search engine or a chatbot. It's a worker. Sometimes it gets things wrong, sometimes it surprises you with initiative. The important part is that you remain in charge. Jules marks a shift in how we think about coding with AI. It's not about faster autocomplete. It's about offloading grunt work, exploring new ideas without context-switching, and even debugging without drowning in stack traces. You become the architect. Jules is your apprentice. Whether you're a solo builder with a side project, a product designer who dabbles in code, or part of a dev team trying to cut through Jira sludge, Jules may very well be your next favorite hire. All you need is a Google account, a GitHub repo, and a task you're too tired to do. Try it. Jules is listening.