Microsoft has released code-testing-generator, an open-source AI agent that automatically generates unit tests for any programming language. The agent uses a 'research-plan-implement' (RPI) pipeline: it scans a repository to detect the language and test framework, then chooses one of three execution paths (direct, single-pass, or iterative) based on scope. It writes tests starting from simple code and progressing to more complex dependencies, then validates quality by checking for weak assertions, missing scenarios, and running the full test suite. The agent is available in the dotnet/skills GitHub repository and integrates with GitHub Copilot CLI, Visual Studio Code, and VS Code Insiders. Currently it supports only unit tests; integration, E2E, browser, and performance tests are out of scope.
Questions this post answers
What is Microsoft's code-testing-generator agent and how does it work?
code-testing-generator is an open-source AI agent that automatically writes and validates unit tests for any programming language. It uses a 'research-plan-implement' (RPI) pipeline: first scanning the repository to detect the language, test framework, and existing tests, then choosing one of three paths (direct, single-pass, or iterative) based on scope, and finally validating tests by checking for weak assertions, missing scenarios, and running the full test suite. Developers evaluating AI test-generation tools track releases like this on daily.dev.
Where can I find and use Microsoft's code-testing-generator agent?
The code-testing-generator agent is available in the dotnet-test plugin inside the dotnet/skills repository on GitHub. It integrates with GitHub Copilot CLI and is also available in Visual Studio Code and VS Code Insiders through plugin support, which is currently a preview feature. It supports unit tests only — integration, E2E, browser, and performance tests are outside its current scope. Teams adopting AI-assisted testing workflows find relevant tooling news on daily.dev.