Tabnine readies AI-generated unit testing for developers

Tabnine, creator of an AI-powered coding assistant for developers, has released a tool to provide automated code testing.

Released on February 22 and now in beta, Tabnine’s unit test generation capability uses artificial intelligence to generate unit tests for your code automatically, with the goal of ensuring fewer bugs and more code stability. Supported programming languages ​​include Python, Java, and JavaScript.

Part of the Tabnine Enterprise coding assistant platform, the unit test generation tool learns from code as it is written. The more the tool is used, the better it becomes at generating unit tests that match a developer’s coding style and patterns, Tabnine said.

Developers can sign up for the beta program on the Tabnine website. The service can be integrated with Microsoft’s Visual Studio code editor and JetBrains IDEs. General availability of test generation capacity is scheduled for the second quarter of this year.

Tabnine previously introduced Tabnine Enterprise, an AI assistant for software developers that provides full-line code completion and promises to automate the creation of boilerplate code. The company said its generative AI models are trained only on repositories with permissive open source licenses, from places like GitHub and other sources.

Tabnine, in a February 23 blog post, cited the differences between Tabnine Enterprise and GitHub Copilot Enterprise, saying that the two technologies differed in areas such as code privacy, open source compliance, and training AI models in private code. GitHub is facing a class action lawsuit claiming that GitHub Copilot violates the legal rights of open source software creators.