Tabnine unveils AI developer ‘coach’ with personalized code review agent – SiliconANGLE

Artificial intelligence code assistant developer Tabnine Ltd. today unveiled a new AI software validation agent designed to help developers produce higher quality, more secure code by enforcing best practices called the Code Review Agent.

As developers work on code, AI coding assistants and agents have already become part of their process for enhancing performance for generating code. However, when it comes time to merge code back into a repository with a pull request, it’s still largely a human review process.

Tabnine said the new Code Review Agent will assist with reviewing code on pull requests by allowing development teams to codify institutional knowledge, corporate policies and software development standards together to help “coach” developers. It will use this information, including awareness of best practices and patterns from what is known as “golden code repos,” in business codebases.

Tabnine has built a hyper-personalized approach to its AI code generation through context awareness of local code and the company’s software repository. The company said this allows it to adapt to each company’s and team’s methods and preferences, which gives its agents intricate know-how for fixing issues and providing assistance.

“AI in software development is about much more than just generating more code; its greatest power might be in helping improve the quality, security and compliance of code in real-time as we work,” said Tabnine President Peter Guagenti. “By reviewing code at the pull request and ensuring that the code presented matches each team’s unique expectations, we are saving engineering teams significant time and effort.”

When a developer requests a merge of their code with the main codebase, the Code Review Agent checks their code in the request against the rules written by the team. These rules can be written in plain English, which means they can be easy to review and maintain over time. If the agent discovers issues with the code, it flags them and provides easy-to-understand guidance and coaches them on how to align their work with standards.

Administrators have complete control over specific rules and can enable or disable them and set the severity.

“Tabnine’s unique approach to personalization allows our agents to behave like a fully onboarded member of your engineering team that is steeped in your team’s ways of working,” said Guagenti.

The company said that the Code Review Agent will also soon be available within code editing software Tabnine supports, where it will passively review code in the background and flag issues. It will act as a coach inside the editor by offering suggestions based on rules and best practices before it is triggered, giving developers a chance to repair their code while they work.

The agent is available in private preview for Tabnine enterprise customers, who can request early access.

Images: Pixabay, Tabnine