Tabnine details hyper-personalised AI code review agent
AI code assistant company Tabnine has come forward with its Code Review Agent.
This software validation agent is said to produce quality secure code by using and enforcing a team’s best practices and standards for software development.
The technology helps codify institutional knowledge, corporate policies and software development standards, including best practices and patterns found in golden code repos.
It then enforces adherence to those rules across the software development process.
This explicit guidance builds on Tabnine’s personalised approach to AI code generation through awareness and understanding of both locally available code and data in the integrated development environment (IDE) and a company’s software repository.
The tool allows users to provide the specific parameters they would like to see their code comply with via plain language. It converts this provided knowledge into a set of rules.
Additionally, it offers predefined rules including commonly used industry standards, as well as language or product-specific best practices.
Pull reviews, pull requests
When developers create a pull request, the Code Review Agent checks the code in the pull request against the rules established by their team. If any aspect of the code doesn’t conform with those rules, then the agent flags it to the code reviewer, providing guidance on the issue and suggested edits to fix it.
All of the rules are in plain English for easier review and maintainence over time.
Tabnine administrators have complete control and can enable or disable specific rules, and set the severity of rules
“AI in software development is about much more than just generating more code; it’s greatest power might be in helping improve the quality, security and compliance of code in real time as we work. 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 while applying a level of rigour to the automation of code review that was never possible with static code analysis,” said Peter Guagenti, president at Tabnine. “Using a set of rules personalised to each given organisation, the Tabnine Code Review Agent sets a new bar for the category. Tabnine’s unique approach to personalisation allows our agents to behave like a fully onboarded member of your engineering team that is steeped in your team’s ways of working.”
Tabnine’s Code Review Agent will also soon be available within the full array of IDEs the company supports. The Agent passively reviews code as a developer works; flagging issues and offering suggestions as appropriate inside the code editor.
