Google Launches Jules: An AI Coding Assistant to Automate Developer Workflows with GitHub Integration
Initially introduced in December 2024 and tested extensively during its beta phase, Jules is now available to the public, marking a major milestone in Google's mission to embed artificial intelligence deeper into the developer ecosystem. Unlike most traditional coding assistants that operate in-browser or via lightweight plugins, Jules runs independently on a Google Cloud virtual machine (VM). This secure setup allows it to fully clone and operate on a developer's codebase without interrupting local workflows.
'Jules runs tasks asynchronously and automates coding work for developers,' Google shared, adding that the tool can manage a wide range of functions including writing tests, fixing bugs, adding new features, updating dependencies, and even creating audio changelogs. Because the agent can execute multiple tasks in parallel, developers can delegate complex jobs while focusing on other priorities, significantly reducing development cycle times.
One of the key strengths of Jules is steerability — developers aren't left out of the loop. They can review the AI's proposed plan at any stage, make changes, and then let the agent continue its work. After completing a task, Jules provides a comprehensive summary, outlining the actions it took, the reasoning behind those decisions, and a detailed code diff that highlights what was changed.
To make things even smoother, Jules integrates directly with GitHub repositories, letting developers maintain their preferred coding environments without switching tools. During its beta phase, Jules was used by thousands of developers and contributed to over 140,000 code improvements. Based on that feedback, Google has introduced a range of upgrades, including a redesigned interface, faster execution through reusable setups, multimodal input support, and tighter GitHub issue linking.
Importantly, Google has emphasized strong privacy and security measures. According to the company, Jules does not train on private code, and all data remains confined within secure VMs — ensuring developers retain full control over their intellectual property.
Pricing and Availability
To cater to varying user needs, Google has introduced three access tiers:
Introductory Tier: Best for beginners looking to explore Jules' basic capabilities.
Google AI Pro Tier: Designed for regular users, offering five times more usage than the base level.
Google AI Ultra Tier: Tailored for power users handling complex, multi-agent coding projects, with twenty times the base tier's capacity.
These plans are being rolled out immediately to Google AI Pro and Ultra subscribers. In a significant move for the academic community, eligible college students can avail a free one-year subscription to the AI Pro plan, giving them access to advanced tools for learning and real-world software development.
With Jules, Google aims to shift the paradigm of software engineering — bringing AI agents that don't just assist, but autonomously execute development tasks with speed, precision, and security.
Try Our AI Features
Explore what Daily8 AI can do for you:
Comments
No comments yet...
Related Articles
Mint
2 hours ago
- Mint
Google, schmoogle: When to ditch web search for deep research
Searching for the perfect electric car could have taken hours. Instead, I opened ChatGPT, clicked the deep research button and walked away from my computer. By the time I'd made coffee, ChatGPT delivered an impressive 6,800-word report. This year, ChatGPT and other popular AI chatbots introduced advanced research modes. When activated, the AI goes beyond basic chat, taking more time, examining more sources and composing a more thorough response. In short: It's just more. Now free users can access this feature, with limits. Recent upgrades, such as OpenAI's latest GPT-5 model, have made research even more powerful. For the past few months, I've experimented with deep research for complicated questions involving big purchases and international trip planning. Could a robot-generated report help me make tough decisions? Or would I end up with 6,000-plus words of AI nonsense? The bots answered questions I didn't think to ask. Though they occasionally led me astray, I realized my days of long Google quests were likely over. This is what I learned about what to deep research, which bots work best and how to avoid common pitfalls. Deep research is best for queries with multiple factors to weigh. (If you're just getting started, hop to my AI beginner's guide first, then come back.) For my EV journey, I first sought advice from my colleagues Joanna and Dan. But I needed to dig deeper for my specific criteria including a roomy back row for a car seat, a length shorter than my current SUV and a battery range that covers a round trip to visit my parents. I fed my many needs into several chatbots. When I hit enter, the AI showed me their 'thinking." First, they made a plan. Then, they launched searches. Lots of searches. In deep research mode, AI repeats this cycle—search then synthesize—multiple times until satisfied. Occasionally, though, the bot can get stuck in its own rabbit hole and you need to start over. Results varied. Perplexity delivered the quickest results, but hallucinated an all-wheel drive model that doesn't exist. Copilot and Gemini provided helpful tables. ChatGPT took more time because it asked clarifying questions first—a clever way to narrow the scope and personalize the report. Claude analyzed the most sources: 386. Deep research can take 30 minutes to complete. Turn on notifications so the app can let you know when your research is ready. My go-to bot is typically Claude for its strong privacy defaults. But for research, comparing results across multiple services proved most useful. Models that appeared on every list became our top contenders. Now I'm about to test drive a Kia Niro, and potentially spend tens of thousands based on a robot's recommendation. Basic chat missed the mark, proposing two models that are too big for parallel parking on city streets. Other successful deep research queries included a family-friendly San Francisco trip itinerary, a comparison of popular 529 savings plans, a detailed summary of scientific consensus on intermittent fasting and a guide to improving my distance swimming. On ChatGPT and Claude, you can add your Google Calendar and other accounts as sources, and ask the AI to, for example, plan activities around your schedule. Deep research isn't always a final answer, but it can help you get there. Ready for AI to do your research? Switch on the 'deep research" or 'research" toggle next to the AI chat box. ChatGPT offers five deep research queries a month to free users, while Perplexity's free plan includes five daily. Copilot, Gemini and Grok limit free access, but don't share specifics. Paid plans increase limits and offer access to more advanced models. Claude's research mode requires a subscription. Here are tips for the best results: Be specific. Give the AI context (your situation and your goal), requirements (must-haves) and your desired output (a report, bullets or a timeline). Chatbots can't read your mind…yet. Enable notifications. Deep research takes time. Turn on notifications so the app can ping you when your response is ready. Verify citations. AI can still make mistakes, so don't copy its work. Before making big decisions, click on citations to check source credibility and attribution. Summarize the output. Reports can be long. Ask for a scannable summary or table, then dive into the full text for details. Understand limitations. The information is only as good as its sources. These chatbots largely use publicly available web content. They can't access paywalled stuff, so think of it as a launchpad for further investigation. Whatever the imperfections of deep research, it easily beats hours and days stuck in a Google-search black hole. I have a new research partner, and it never needs a coffee break. News Corp, owner of Dow Jones Newswires and The Wall Street Journal, has a content-licensing partnership with OpenAI. Last year, the Journal's parent company, Dow Jones, sued Perplexity for copyright infringement.
India Today
4 hours ago
- India Today
Last-minute Pixel 10 leak says no SIM tray, launch in 10 days at Made by Google event
Rumours are swirling once again in Pixel land, and this time they could spell a rather big change for Google's upcoming flagship series. The Pixel 10 family, expected sometime next year, might just wave goodbye to a little metal component that's been a part of every smartphone since the early days: the humble SIM card to a fresh post by well-known tipster Evan Blass on X (formerly Twitter), Google is allegedly plotting to strip the physical SIM slot from three of its next-gen handsets: the Pixel 10, Pixel 10 Pro, and Pixel 10 Pro XL. Instead, these devices would rely entirely on eSIM technology, specifically, two active eSIM slots to keep you connected. In other words, if this leak is accurate, you'll never have to poke your phone with that little pin again, though you might also lose the ability to quickly swap SIMs on the Blass claims the Pixel 10 Pro Fold, the foldable expected to launch alongside the rest of the line-up, will still hang on to its physical SIM tray. It's almost as if Google has decided foldable owners deserve that extra bit of old-school flexibility. But there's another wrinkle: Blass responded to one curious follower asking whether this SIM tray removal would be a global decision or a region-specific one. His answer? The eSIM-only move could be limited to the United States. If that's the case, buyers in other markets might still get their beloved SIM slot, though, as always, that remains while the leak is intriguing, it's far from bulletproof. For starters, Blass is usually a deadpan, detail-first type of tipster, but this post began with an oddly vague 'tipster suggests' intro, unusual for someone with his track record. Then there's the matter of other Pixel 10 leaks we've already seen. Early CAD-based renders showed a perfectly ordinary SIM slot across all models. Even real-life prototype images that surfaced online featured a SIM tray in the frame. That doesn't exactly scream 'eSIM revolution'.It's also worth pointing out that the images we've seen in recent weeks haven't shown the top edge of the phone in great detail, which is where the SIM slot would usually be visible. That leaves just enough mystery for speculation to thrive. And thrive it has: the replies under Blass's post quickly filled with strong Pixel fans see this potential change as inevitable. Apple has already gone eSIM-only with its US iPhone 14 and 15 models, and the writing could be on the wall for physical SIMs in certain regions. eSIMs can make devices more waterproof, free up internal space for other components, and simplify network switching for those comfortable doing everything however, are less enthusiastic. Travellers, in particular, often prefer a physical SIM slot because it makes buying and popping in a local SIM card quick and painless. With eSIMs, the process can be more fiddly – and if your phone breaks, transferring an eSIM to another device isn't always as straightforward as swapping a Google does follow through with this change, it could find itself walking a tightrope between innovation and alienating a chunk of its audience. In the US, the transition to eSIMs has been slow but steady, with major carriers embracing the tech. Still, there are plenty of people who simply like the reassurance of having a physical card they can hold in their course, there's every chance this rumour turns out to be a false alarm, or at least a premature one. Google might be testing eSIM-only models internally, or exploring a regional rollout, without committing to ditching the SIM tray everywhere. After all, smartphone manufacturers often trial multiple hardware configurations before settling on the final production we see more concrete leaks, or hear from Google itself, it's wise to keep the salt shaker handy. But if you're a die-hard SIM card loyalist living in the US, you might want to brace yourself for the possibility that your next Pixel could be missing that little slot you've been using for years. On the bright side, you'll no longer have to rummage through drawers looking for that fiddly SIM ejector tool.- Ends
Indian Express
4 hours ago
- Indian Express
Free AI courses for beginners that does not require any prior experience
Artificial Intelligence is no longer the future — it is our present, which is already shaping our daily lives. Whether you're curious about how AI works or aiming to build a tech-driven career, now is the perfect time to start learning. With rapid demand, several top organisations have started to offer free beginner-friendly AI courses that make this journey accessible to everyone. From IBM's AI for Everyone on edX to Google Cloud's Introduction to Generative AI, and practical modules from Microsoft, HP LIFE, and SkillsBuild, this article highlights a collection of courses that open the door to the world of artificial intelligence. Let's get started and dive into the possibilities AI can unlock for you with these self-paced courses. Top free coding courses offered by Google, MIT, Harvard IBM offers a self-paced learning course that introduces the basics of Artificial Intelligence, followed by modules on Generative AI, AI Ethics, and more. To get started, simply create a free account on IBM's learning platform. This course is ideal for beginners looking to build a foundation in AI concepts and frameworks for their future career. Interested to know further: Not only this, but you can also do another IBM course on edX that will help learners understand machine learning, deep learning and neural networks. The best part of the above two courses is that you do not need any prior experience, and you can proceed at your speed. Want to know more? Head to this: Google Cloud's Machine Learning and AI training platform claims to offer a comprehensive suite of courses designed for learners at every skill level—from curious beginners to seasoned developers. The curriculum includes foundational concepts, hands-on labs, and advanced tools like Vertex AI, BigQuery ML, and TensorFlow. Along with diving deep into generative AI, conversational agents with Dialogflow CX, and machine learning operations (MLOps) for production-ready systems. Want to explore more? move to this: Microsoft's Use AI for Everyday Tasks module is a beginner-friendly guide to integrating generative AI into daily life. It introduces core concepts like prompting and responsible AI use, with some practical applications at home and work—such as drafting emails, organising study plans, or even creating podcasts. With no prerequisites required, it can be a great starting point for anyone curious about how AI can boost productivity and creativity in everyday routines. Babson College's AI for Leaders course on edX is for executives, managers, and board members to thrive in an AI-driven world. This self-paced, four-week programme blends over 40 video lectures, more than 25 exercises, and real-world case studies to help learners understand how AI transforms business models, customer engagement, operations, and competitive strategy. HP LIFE's AI for Beginners course offers a free, flexible introduction to artificial intelligence for anyone curious about how AI is shaping the world. Developed in partnership with UNIDO, this course explores key concepts like machine learning, generative AI, and large language models, while highlighting the role of data in AI systems. Learners also gain insights into AI ethics, legal frameworks, and emerging trends that are redefining industries, education, and everyday life. With a certificate upon completion, the course can be completed by anyone, from students to professionals to entrepreneurs. To know more? visit: Whether you are a curious student, an ambitious professional, or someone simply fascinated by the potential of artificial intelligence, these free beginner-friendly and self-paced AI courses can be your gateway to a bright and tech-savvy future.
