Google has taken a significant step forward in its AI-powered coding initiative, announcing support for third-party tools in Gemini Code Assist, its enterprise-focused code completion service. This move is expected to further enhance the capabilities of Code Assist, which was launched in April as a rebrand of a similar service previously offered under the Duet AI branding.

Code Assist, available through plug-ins for popular development environments like VS Code and JetBrains, leverages Google's Gemini AI models to reason over and change large chunks of code. With the addition of third-party tools, which are launching in private preview, Code Assist can now pull in real-time data and access information from outside applications. This integration aims to bring various technologies into the coding environment while minimizing potential distractions, according to Google director of product management Ryan Salva and group product manager Prithpal Bhogill.

The new tools feature is designed to eliminate the friction of context switching, allowing developers to focus on writing great code while accessing solutions for productivity, observability, security, databases, and more. As Salva and Bhogill noted in a blog post, "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."

At launch, Code Assist tools from prominent partners such as GitLab, GitHub, Sentry.io, Atlassian Rovo, Snyk, and Google's own Google Docs are available. However, not just anyone can build a tool for Code Assist; Google is limiting the program to Google Cloud partners, at least for now. Interested partners can reach out to their partner managers to explore the possibility of creating new tools.

Code Assist is a direct competitor to GitHub's Copilot Enterprise, which offers extensions that work similarly to Code Assist tools. However, Google has long emphasized that Code Assist stands out in other ways, such as its support for codebases that sit on-premises. This year, Code Assist has seen a number of upgrades, including enhanced code transformation capabilities and the launch of an enterprise plan with customized code suggestions based on private code repositories.

Despite security, copyright, and reliability concerns surrounding AI-powered assistive coding tools, developers have shown enthusiasm for them. According to GitHub's latest poll, the vast majority of respondents have 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.

The integration of third-party tools with Code Assist marks a significant milestone in the development of AI-powered coding tools. As the technology continues to evolve, it will be interesting to see how it shapes the future of software development and the role of developers in the process.