A developer of a tool that completes AI code, Tabnine, has announced its integration with GitLab so that developers can collaborate in a better way using their custom AI code models.

Tabnine uses AI models to make predictive suggestions for developers typing code to speed up the development session. Tabnine collaborates with GitLab’s private repository, which will help automate most repetitive coding developers do every day, like writing standard statements, forming syntax, and producing functions.

GitLab’s global VP of alliances, Nima Badiey, had this to say about the new collaboration, when speaking to SiliconANGLE: “Just think about the amount of time you waste on your phone correcting autocorrect, or how quickly you can write in Gmail with the suggestions on, code is pretty much repeatable patterns, and people tend to write from scratch what they could mostly automate.”

An AI agent that automatically suggests the code needed is so useful because developers usually have to work on two screens, one for editing, the other with the GitLab repository. With the predictive text, they won’t need to look at the other screen, which can be a hassle.

Brandon Jung, the VP of business development and ecosystems at Tabnine had the following to remark on the collaboration:“Over the past six to eight months, we’ve been working on custom models, which takes the strength of the big universal model, but we can take your private code and build you a model that dramatically ups the security and quality of your code.  This is because, of course, you already know it’s a solid codebase. That’s hugely valuable, you’re not just taking some random open-source code and integrating it. So, you can bring new developers into your team, and they’re getting the best suggestions from your own codebase.”

More about custom AI models

You can also use these models in many other ways, such as different levels of work. For example, a junior developer who is just learning will require AI suggestions more than a senior coder. This will help them become better at coding and learning it faster.