Latest news with #Korevec
Yahoo
06-08-2025
- Business
- Yahoo
Google's AI coding agent Jules is now out of beta
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. From vibe coding to mobile use, beta trials informed Jules development 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. Error in retrieving data Sign in to access your portfolio Error in retrieving data Error in retrieving data Error in retrieving data Error in retrieving data
Time of India
22-05-2025
- Business
- Time of India
Google introduces Stitch AI-powered tool for app design and development at Google I/O 2025
Google unveiled various important tools at its annual developer conference Google I/O 2025 . At the same event, the tech giant also introduced 'Stitch' its new AI-powered tool which is designed to bridge the gab between design and development of app creation. Tired of too many ads? go ad free now The company claims that Stitch aims to transform how user interfaces (UIs) are conceptualized and built, making app design more accessible and efficient for both seasoned professionals and aspiring creators. 'Introducing a new AI-powered tool to generate high-quality UI designs and corresponding frontend code for desktop and mobile by using natural language descriptions or image prompts. Stitch lets users bring ideas to life, lightning fast. Iterate on your designs conversationally, adjust themes, and easily export your creations to CSS/HTML or Figma to keep going,' said Google in a blog post. How Stitch works Stitch allows users to: Generate HTML and CSS markup for app designs using simple prompts. Choose between Gemini 2.5 Pro and Gemini 2.5 Flash AI models for interface ideation. Export designs directly to Figma or refine code in an Integrated Development Environment (IDE). Fine-tune UI elements with customisation options for themes, fonts, and layouts Google product manager Kathy Korevec described Stitch as a tool for rapid iteration, enabling users to quickly prototype and refine app designs. 'What we want to do is make it super easy and approachable for people to take their design thinking to the next level,' Korevec stated.
Techday NZ
22-05-2025
- Techday NZ
Google launches Jules globally, an AI coding agent for GitHub
Google Labs has announced that Jules, its asynchronous coding agent, is now available in public beta for users worldwide. Jules, first introduced in December as a preview, differs from traditional code-completion tools or co-pilots by operating as an autonomous agent capable of reading code, understanding user intent, and carrying out tasks with minimal intervention. Jules is designed to integrate directly with existing code repositories by cloning the codebase into a secure Google Cloud virtual machine. Once integrated, it completes tasks such as writing tests, building new features, providing audio changelogs, fixing bugs, and updating dependency versions. This approach allows users to focus on other activities while Jules works independently in the background. "Jules is an asynchronous, agentic coding assistant that integrates directly with your existing repositories. It clones your codebase into a secure Google Cloud virtual machine (VM), understands the full context of your project, and performs tasks such as: Writing tests, building new features, providing audio changelogs, fixing bugs, and bumping dependency versions. 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," said Kathy Korevec, Director, Product Management at Google Labs. Security and privacy are key aspects of the platform. Jules is private by default, with user data remaining isolated within the execution environment, and there is no training of AI models on private code. The coding agent builds on Google's Gemini 2.5 Pro language model. This enables Jules to perform advanced reasoning and make multi-file changes across projects. By leveraging the cloud virtual machine setup, it can handle concurrent and complex tasks efficiently. "We're at a turning point: agentic development is shifting from prototype to product and quickly becoming central to how software gets built. Jules uses Gemini 2.5 Pro, giving it access to some of the most advanced coding reasoning available today. Paired with its cloud VM system, it can handle complex, multi-file changes and concurrent tasks with speed and precision," Korevec stated. Jules does not require a sandbox environment, instead operating on production codebases with full project context. Users benefit from parallel execution of tasks, handled within the cloud virtual machine, and have visibility into Jules' proposed workflow through visible plans and reasoning prior to any code changes being applied. The platform integrates with GitHub, enabling workflows directly within the familiar repository interface without additional context switching or setup. Users can adjust plans before, during, or after execution for greater control, and an audio changelog feature provides a contextual narration of recent commits. "Here's a look at what you get with Jules: Works on real codebases: Jules doesn't need a sandbox. It takes the full context of your existing project to reason about changes intelligently. Parallel execution: Tasks run inside a cloud VM, enabling concurrent execution. It can handle multiple requests simultaneously. Visible workflow: Jules shows you its plan and reasoning before making changes. GitHub integration: Jules works where you already do, directly inside your GitHub workflow. No context-switching, no extra setup. User steerability: Modify the presented plan before, during, and after execution to maintain control over your code. Audio summaries: Jules offers an audio changelog of recent commits, turning your project history into a contextual changelog you can listen to," Korevec explained. During the initial public beta phase, Jules is available without charge, though users may be subject to usage limits. Details about these limitations are provided in the platform's documentation. Google Labs anticipates introducing a pricing structure once the platform moves beyond the beta stage and as features continue to be developed and refined.
Yahoo
20-05-2025
- Business
- Yahoo
Stitch is Google's AI-powered tool to help design apps
At the Google I/O 2025 developer conference, Google launched Stitch, an AI-powered tool to help design web and mobile app front ends by generating the necessary UI elements and code. Stitch can be prompted to create app UIs with a few words or even an image, providing HTML and CSS markup for the designs it generates. Users can choose between Google's Gemini 2.5 Pro and Gemini 2.5 Flash AI models to power Stitch's code and interface ideation. Stitch arrives as so-called vibe coding — programming using code-generating AI models — continues to grow in popularity. There's a number of large tech startups going after the burgeoning market, including Cursor maker Anysphere, Cognition, and Windsurf. Just last week, OpenAI launched a new assistive coding service called Codex. And yesterday during its Build 2025 kickoff, Microsoft rolled out a series of updates to its GitHub Copilot coding assistant. Stitch is a bit more limited in what it can do compared to some other vibe coding products, but there's a fair amount of customization options. The tool supports directly exporting to Figma and can expose code so that it can be refined and worked on in an IDE. Stitch also lets users fine-tune any of the app design elements it generates. In a demo with TechCrunch, Google product manager Kathy Korevec showed two projects created using Stitch: a responsive mobile UI design for an app for bookworms and a web dashboard for beekeeping. "[Stitch is] where you can come and get your initial iteration done, and then you can keep going from there," said Korevec. "What we want to do is make it super, super easy and approachable for people to do that next level of design thinking or that next level of software building for them." Soon after I/O, Google plans to add a feature that'll allow users to make changes in their UI designs by taking screenshots of the object they want to tweak and annotating it with the modifications they want, Korevec said. She added that while Stitch is reasonably powerful, it isn't meant to be a full-fledged design platform like Figma or Adobe XD. Alongside Stitch, Google has expanded access to Jules, its AI agent aimed at helping developers fix bugs in their code. Now in public beta, the tool helps developers understand complex code, create pull requests on GitHub, and handle certain backlog items and programming tasks. In a separate demo, Korevec showed Jules upgrading a website running the deprecated version 16 to 22. Jules cloned the site's codebase in a clean virtual machine and shared a "plan" for the upgrade, which Korevec was then prompted to approve. Once the upgrade was completed, Korevec asked Jules to verify that the website still worked correctly — which Jules did. Jules currently uses Gemini 2.5 Pro, but Korevec told TechCrunch that users will be able to switch between different models in the future. This article originally appeared on TechCrunch at Error in retrieving data Sign in to access your portfolio Error in retrieving data Error in retrieving data Error in retrieving data Error in retrieving data
