Google on Wednesday announced the launch of an experimental AI code assistant called “Jules”, designed to help developers automatically fix code errors.
The tool was released on December 11 with Gemini 2.0, which uses an updated Google artificial intelligence model to create multi-step plans to solve problems, modify multiple files, and prepare pull requests for Python and Javascript coding tasks in GitHub workflows.
Last year, Microsoft introduced similar functionality for its GitHub Copilot, which can identify and interpret code and provide modification suggestions and fixes for errors. Jules will compete directly with Microsoft’s products, as well as tools such as Cursor, as well as Claude and ChatGPT.
Google’s launch of an AI assistant focused on coding is not surprising – back in October, Google CEO Sundar Pichai said that more than a quarter of the company’s new code is now generated by AI.
It was noted that Google said in its blog post: “Jules can fix bugs and handle other time-consuming tasks, allowing developers to focus on what they really want to build.” “This work is part of our long-term goal of building AI agents that are helpful in all areas, including coding.”
Developers have full control to review and tweak the solutions created by Jules before choosing to merge its generated code into their projects.
The announcement did not mention that Jules would be able to proactively find bugs, so presumably, it would need to be pointed to a list of issues that have already been identified for fixes.
Google also said that Jules is still in early development and “might make mistakes,” but internal testing has shown it to help improve developer productivity and provide real-time updates to help track and manage tasks.
According to Google, Jules is rolling out to a “select group of trusted testers” and will be released to other developers in early 2025, with updates on its availability and development progress being provided on the Google Labs website.