Tabnine Introduces AI-Powered Code Review Agent for Enhanced Developer Productivity

Tabnine unveils AI developer 'coach' with personalized code review agent - SiliconANGLE

Tabnine unveils AI developer 'coach' with personalized code review agent 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.

Tabnine launches its code review agent

AI code assistant company Tabnine is launching a code review agent today that aims to help developers stick to their organization's best practices and standards. It allows organizations to codify these rules either by providing the agent with documentation or by pointing it at a set of "golden code repos." The agent will passively review the code as the developer works in the IDE, flag issues as it spots them, and offer fixes when able. As Tabnine President and CMO Peter Guagenti told me, many companies -- and the developers they employ -- aren't even aware of the rules and best practices in their own documentation. While one of Tabnine's core tenants has always been to customize the agents based on an organization's needs, the company also partnered with companies like Redis to collect some of their best practices and pre-trained its models on that. Starting today, Tabnine is opening this up to other vendors who want to provide their rules, too. "Database companies are a great example of this," he said. "Each one has its own pattern. Each one has its own ways of working that have good and bad outcomes -- and when it has a bad outcome, they blame the product, not the code, right? So we think this is a great opportunity for AI to correct the behavior and actually make the products more successful." Developers can turn these pre-trained rules on and off as needed. As for how correct the suggestions are, Tabnine argues that its review agents read the code like a human would. That also means that if the code is really obscure, it might miss an issue. But unlike human reviewers, it will read every line of code and not just skim. It's surely no coincidence that Tabnine is making today's announcement on the first day of GitHub's Universe conference. GitHub's Copilot, after all, surely has the majority of the brand awareness among AI coding tools. But Guagenti doesn't seem to worry too much about competing with GitHub. "We think the business will stratify," he said. "We think folks like Cursor and others, they'll eat up the bottom of the market because a lot of people don't want to write code. We think Copilot has to go for the fat middle -- it has to be 80% for as many people as possible. However, that wasn't [Tabine co-founders] Dror [Weiss's] and Eran [Yahav's]vision. Their vision was: how do I make the top 1,000 engineering teams in the world more productive, more successful, and write better applications? That vision is now starting to really come together."