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.

Image: Google