Qodo unveils fully autonomous AI regression testing agent to address growing code quality challenges
In the first-ever case of an AI agent autonomously contributing to a major open source project, Qodo's agent contributed 15 regression tests to a popular repository created by Hugging Face
TEL AVIV, Israel, Dec. 4, 2024 /PRNewswire/ -- Qodo (formerly CodiumAI), the generative AI code integrity platform, today announced Qodo Cover, a fully autonomous AI regression testing agent that generates comprehensive test suites for software applications. The announcement was made during AWS re:Invent 2024, where Qodo was selected as a finalist in the AWS Unicorn Tank Pitch Competition.
AI-generated code has become increasingly pervasive in software development, with Google recently revealing that 25% of their new code is AI-generated. Ensuring code quality and maintainability is now more critical than ever. Unit testing, and regression testing in particular, which verifies that existing functionality remains intact as code evolves, are essential for software reliability and maintainability but often receive insufficient attention due to time constraints and competing priorities.
Qodo Cover generates regression tests by analyzing source code, then validates each test to ensure it runs successfully, passes, and increases code coverage. Only tests that meet all these criteria are kept, ensuring every generated test adds value. The agent can be deployed either as a GitHub action that automatically creates pull requests with suggested unit tests for newly changed code, or as a comprehensive tool that analyzes entire repositories to identify and close coverage gaps by extending existing test suites. Developers maintain full control over the process by reviewing and selectively accepting generated tests, ensuring they align with project standards and best practices.
"We're fast approaching a point where the vast majority of code will be AI-generated, fundamentally changing how software is built," said Itamar Friedman, CEO of Qodo. "It's critical that we keep up by leveraging AI not just for code generation, but for maintaining and improving code quality. Qodo Cover represents a significant step toward autonomous software development by ensuring every piece of code, whether human or AI-written, is properly tested and maintainable."
Recently, a pull request generated fully autonomously by Qodo Cover containing 15 unit tests was accepted into Hugging Face's PyTorch Image Models repository – a highly popular machine learning project with over 30,000 GitHub stars and used by more than 40,000 other projects. This demonstrates the solution's ability to generate production-quality tests that meet the standards of leading open-source projects.
Built on Qodo's open-source Cover Agent project, Qodo Cover supports all of the popular AI models including Claude 3.5 Sonnet and GPT-4o. It delivers consistently high-quality results across more than a dozen programming languages — including JavaScript, TypeScript, Java, C++, PHP, C#, Ruby, Go, Rust, and C — and works with various testing frameworks and coverage reporting tools. Each pull request includes detailed coverage improvement reports, helping teams track their testing progress.
Looking ahead, Qodo Cover will integrate seamlessly with Qodo Merge and Qodo Gen, creating a comprehensive suite of tools that work together to ensure code quality throughout the development lifecycle.
Contact:
Gavriel Cohen
Concrete Media for Qodo
[email protected]
SOURCE Qodo
Share this article