Google Enhances Gemini Code Assist with Third-Party Tool Integration

Google's business AI coding platform now supports third-party tools

Google has announced a handy update to its Gemini Code Assist platform, expanding the AI-powered coding assistant's capabilities even further by including support for third-party data sources. "[Gemini Code Assist tools] enable developers to retrieve information from, or act on any part of their engineering system, which is especially helpful for services outside the IDE," noted a blog post update by Senior Director for Product Management Ryan J Salva and Group Product Manager Prithpal Bhogill. The news comes shortly after the tech giant announced its latest Gemini Flash 2.0 model, which the company hopes will produce higher-quality responses with lower latency. Salva and Bhogill highlighted how the update will enable developers to work more seamlessly with uninterrupted flows; third-party integrations will surface information and tools from other applications without having to leave the IDE. Google also says that by having access to more data and insights, more efficient development cycles, reduced errors and better software are all possible. Already, Atlassian (Rovo), GitHub, GitLab, Google Docs, Sentry and Snyk have all been announced as launch partners, offering full support for Gemini Code Assist tools. Atlassian Head of Product for Agile and DevOps AI, Josh Devenny, commented: "This integration ensures every developer can instantly access technical specifications, tasks in progress, blockers, or even identify the right person to ask for help, all without leaving their coding environment." Google also boasted about how it can support other businesses, saying the launch of its new tools will enhance developers' productivity and "[provide] immense value to [its] partners, offering exciting new opportunities for growth and engagement." Developers can express their interest in joining the Gemini Code Assist tools private preview, and signups are also open to use Gemini 2.0 Flash in Gemini Code Assist.

Google expands Code Assist with support for third-party data sources - SiliconANGLE

Google expands Code Assist with support for third-party data sources Google LLC is updating its Code Assist tools that are designed to help increase developed productivity from within integrated development environments such as JetBrains and Visual Studio Code. In a blog post, Google Director of Product Management Ryan Salva and Group Product Manager Prithpal Bhogill said Code Assist will now be powered by Gemini 2.0, the company's most advanced large language model, which supports a longer context window. That means it can understand larger code bases than before. In addition, Google is planning to launch various new Gemini Code Assist tools in private preview. They'll connect it to data sources such as GitHub, GitLab, Google Docs, Atlassian, Sentry.io and Snyk. This will make it possible for developers to ask Code Assist to help them from directly within their IDEs. Before this, Code Assist could only connect to IDEs. These updates make it possible for Code Assist to pull in real-time data and access information from third-party applications. Access to the new Code Assist is currently limited to Google Cloud partners. Salva and Bhogil explained that the idea with the updates is to enable coders to add more context to their work, without interrupting their workflows. "This new tools feature can help eliminate the friction of context switching," Salva and Bhogill wrote. "Getting scalable, secure applications into production requires more than just writing great code -- developers need solutions for productivity, observability, security, databases and more." Code Assist was formerly known as Duet AI, and was relaunched for enterprises in October. It was seen as Google's response to the growing demand for artificial intelligence-powered coding tools such as GitHub Copilot, adding enterprise-grade security and legal indemnification features. With that update, it also received enhanced code transformation capabilities and customized code suggestions, based on customer's private code repositories. Developers have shown massive enthusiasm for AI-powered programming assistants, despite concerns over security, copyright and reliability. In a recent poll by GitHub, the vast majority of developers indicate they have adopted AI tools in some form, while GitHub Copilot itself has more than 1.8 million paying customers.

Code Assist, Google's enterprise-focused coding assistant, gets third-party tools | TechCrunch

Google on Tuesday announced support for third-party tools in Gemini Code Assist, its enterprise-focused AI code completion service. Code Assist launched in April as a rebrand of a similar service Google offered under its now-defunct Duet AI branding. Available through plug-ins for popular dev environments like VS Code and JetBrains, Code Assist is powered by Google's Gemini AI models, which allow it to reason over and change large chunks of code. With the addition of tools, which are launching in private preview, Code Assist can pull in real-time data and access info from outside applications. The idea is to bring various technologies into the coding environment while minimizing potential distractions, said Google director of product management Ryan Salva and group product manager Prithpal Bhogill. "This new tools feature can help eliminate the friction of context switching," Salva and Bhogill jointly wrote in a blog post. "Getting scalable, secure applications into production requires more than just writing great code -- developers need solutions for productivity, observability, security, databases, and more." Not just anyone can build a tool for Code Assist. Google is limiting the program to Google Cloud partners, at least for now. "Tools enable developers to retrieve information from, or act on, any part of their engineering system -- which is especially helpful for services outside the developer environment," Salva and Bhogill wrote. "For example, you might summarize recent comments from a Jira issue, find the last person who merged changes to a file in git, or show the most recent live site issue from Sentry." Code Assist tools from GitLab, GitHub, Sentry.io, Atlassian Rovo, Snyk, and Google's own Google Docs are available at launch. Google Cloud partners interested in creating new tools can reach out to their partner managers, Salva and Bhogill say. Code Assist is a direct competitor to GitHub's Copilot Enterprise, which offers extensions that work a lot like Code Assist tools. But Google has long asserted that Code Assist stands out in other ways, for example in its support for codebases that sit on-premises. Code Assist has seen a number of upgrades this year, including enhanced code transformation capabilities and the launch of an enterprise plan with customized code suggestions based on private code repositories. Despite the security, copyright, and reliability concerns around AI-powered assistive coding tools, developers have shown enthusiasm for them, with the vast majority of respondents in GitHub's latest poll saying that they've adopted AI tools in some form. GitHub reported in April that Copilot had over 1.8 million paying users and more than 50,000 business customers.

Google upgrades its programming agent Code Assist with Gemini 2.0, adds source integrations

Code Assist will now run on the recently released Gemini 2.0, offering a larger context window to understand bigger code bases from enterprises. Google will also launch Gemini Code Assist tools in a private preview. The platform will connect to data sources like GitLab, GitHub, Google Docs, Sentry.io, Atlassian and Snyk. This will allow developers and other coders to ask Code Assist for help directly in their IDEs. Previously, Code Assist connected to VS Code and JetBrains. Google Cloud senior director for product management Ryan J. Salva told VentureBeat in an interview that the idea is to allow coders to add more context to their work without interrupting their flow. Salva said Google will add more partners in the future. Formerly Duet AI, Code Assist was launched for enterprises in October. As organizations sought ways to streamline coding projects, demand for AI coding platforms like GitHub Copilot grew. Code Assist added enterprise-grade security and legal indemnification when the enterprise option was released. AI where developers work Salva said connecting Code Assist to other tools developers use provides more context for their work without them having to simultaneously open multiple windows. "There's so many other tools that a developer uses in the course of a day," Salva said. "They might use GitHub or Atlassian Jira or DataDog or Snyk or all these other tools. What we wanted to do is to enable developers to bring in that additional context to their IDE." Salva said developers just need to open the Code Assist chat window and ask it to summarize the most recent comments for particular issues or the most recent pull requests on repositories, "so that it queries the data source and brings the context back to the IDE and [the] large language model can synthesize it." AI code assistants were some of the first significant use cases for generative AI, especially after software developers began using ChatGPT to help with coding. Since then, a slew of enterprise-focused coding assistants have been released. GitHub released Copilot Enterprise in February, and Oracle launched its Java and SQL coding assistant. Harness came out with a coding assistant built with Gemini that gives real-time suggestions. Meanwhile, OpenAI and Anthropic began offering interface features that let coders work directly on their chat platforms. ChatGPT's Canvas lets users generate and edit code without copying and pasting it elsewhere. OpenAI also added integrations to tools like VS Code, XCode, Terminal and iTerm 2 from the ChatGPT MacOS desktop app. Meanwhile, Anthropic launched Artifacts for Claude so Claude users can generate, edit and run code. Not Jules Salva pointed out that while Code Assist now supports Gemini 2.0, it remains wholly separate from Jules, the coding tool Google announced during the launch of the new Gemini models. "Jules is really one of the many experiments to emerge out of the Google Labs team to show how we can use autonomous or semiautonomous agents to automate the process of coding," Salva said. "You can expect that over time, the experiments that graduate from Google Labs, those same capabilities, might become a part of products like Gemini Code Assist." He added that his team works closely with the Jules team and is excited to see Jules progress, but Code Assist remains the only generally available enterprise-grade coding tool powered by Gemini. Salva said early feedback from Code Assist and Jules users shows great interest in Gemini 2.0's latency improvements. "When you're sitting there trying to code and trying to stay in the flow state, you want those kinds of responses to come up in milliseconds. Any moment the developer feels like they're waiting for the tool is a bad thing, and so we're getting faster and faster responses out of it," he said. Coding tools will continue to grow Coding assistants will still be crucial to the growth of the generative AI space, but Salva said the next few years may see a change in how companies develop code generation models and applications. Salva pointed to the 2024 Accelerate State of DevOps Report from Google's DevOps Research and Assessment team, which showed 39% of respondents distrusted AI-generated code and a decline in documentation and delivery quality. "We have as an industry with AI assistive tools focused largely on throughput productivity improvements and velocity improvements over the course of the last four years," Salva said. "And as we're starting to see that that be associated with a drop in overall stability, I suspect here that the conversation in the next year is really going to shift to how are we using AI to improve quality across multiple dimensions."

Programmers, do you get window-switch whiplash? Google's new Code Assist aims to help

When we last visited Gemini Code Assist back in April, the product was in pre-release. Code Assist ran using Gemini 1.5. Now it's been released and updated to what Google (we haven't tried it yet) says is the much more capable Gemini 2.0. Today, Google is announcing Gemini Code Assist tools, which Ryan J. Salva, senior director, product management, and Prithpal Bhogill, group product manager, describe in today's blog post as a "connected development ecosystem." Also: The most popular programming languages in 2024 They also describe Code Assist tools as "a paradigm shift in how developers get the information they need to build and manage apps." Hmm... David's First Rule of Technology Marketing is if a product manager loves how you describe a benefit, don't use it in your marketing copy. The corollary to David's First Rule is that if your engineers like how the product is described, so will your tech customers. Product managers just love calling their products "paradigm shifts." To be fair, this product involves a combination of generative AI and Google, and we've been experiencing paradigm shifts on an almost daily basis. The pace of change is enough to make you dizzy. But this reality also means we can't just immediately discount Salva and Bhogill's marketing as hyperbole. So, let's explore what Code Assist tools offer, and you can judge whether today's "paradigm shift" is hyperbolic or game-changing. Gemini Code Assist is a code helper that lives inside your development environment, like VS Code or Jetbrains. While you edit code, you can type a prompt and get a response from Code Assist. Also: 25 AI tips to boost your programming productivity with ChatGPT What Salva and Bhogill are announcing today is the integration of third-party tools into Code Assist so you can use those tools from your editing environment. The idea is that programmers won't have to switch to a new window to get to their tools -- what they'll need is literally at the end of a keypress. Right now, Google is announcing integration with the following tools in a private preview: According to Danny Allan, CTO at Snyk: "By collaborating with Google Cloud to build a dedicated Gemini tool, we're empowering developers to use Gemini to write code and Snyk to test and fix it -- all within their IDE." Also: Google's Gemini 2.0 AI promises to be faster and smarter via agentic advances Allan talks about how staying in the interactive development environment (IDE) can help developers concentrate and maintain focus while coding: "This integration ensures developers can stay in their creative flow, leveraging AI to accelerate innovation while maintaining the highest standards of security." Tools like the ones in the list above can help developers achieve that goal. That said, I'm hard-pressed to see why GitHub is included because almost every IDE has tight integration with GitHub out of the box. Perhaps as Google expands its private preview, we'll see what AI features apply to the GitHub integration. Also: The best AI for coding in 2024 (and what not to use) Salva and Bhogill say: "Getting scalable, secure applications into production requires more than just writing great code -- developers need solutions for productivity, observability, security, databases, and more." Google is making sure this announcement is a partner business development pitch as much as it is a tool for developers. The company's two product marketing professionals point to benefits like fostering direct developer connections and expanding reach that provide "opportunities for growth and engagement." The dual benefits statements reflect that powerful external development tools inside the IDE will improve programmer productivity. However, including those tools in the Google Code Assists offering will "extend their reach and brand awareness within the developer community." Google also promises to "proactively co-market with our partners to maximize exposure and tell a cohesive story." Also: 5 reasons why Google's Trillium could transform AI and cloud computing - and 2 obstacles Gemini Code Assist pricing starts at $19 per user per month for the standard service when purchased for an entire year. The enterprise version starts at $45 per user per month when purchased for an entire year. The enterprise version provides codebase awareness for an entire-ish codebase. For an analysis of the limits of those versions, check out my article. The tools add-on for Gemini Code Assist is in private preview, but you can click here to fill out a form and request access. What do you think? Has Google achieved a "paradigm shift" with Gemini Code Assist tools? Do you use Code Assist or any other AI while programming? Let us know in the comments below.