New Amazon Q Developer agent capabilities include generating documentation, code reviews, and unit tests

Last year at AWS re:Invent, we previewed Amazon Q Developer, a generative AI–powered assistant for designing, building, testing, deploying, and maintaining software across integrated development environments (IDEs) such as Visual Studio, Visual Studio Code, JetBrains IDEs, Eclipse (preview), JupyterLab, Amazon EMR Studio, or AWS Glue Studio.

You can also use Amazon Q Developer in the AWS Management Console, AWS Console Mobile Application, Amazon CodeCatalyst, AWS Support, AWS website, or through Slack and Microsoft Teams with AWS Chatbot.

Due to the rapid pace of innovation, we announced the general availability of Amazon Q Developer in April and added more capabilities, such as supporting AWS Command Line Interface (AWS CLI), Amazon SageMaker Studio, AWS CloudShell, as well as inline chat for seamless coding operations in your IDE. AWS was also named as a Leader in the first Gartner Magic Quadrant for AI Code Assistants.

Amazon Q Developer has agents that can generate real-time code suggestions based on your comments and existing code, bootstrap new projects from a single prompt (/dev), automate the process of upgrading and transforming legacy Java applications with the Amazon Q Developer transformation capability (/transform), generate customized code recommendations from your private repositories securely, and quickly understand what resources are running in your AWS account with a simple prompt.

Today, we’re expanding Amazon Q Developer agent capabilities for: 1) enhanced documentation in codebases (/doc), 2) supporting code reviews to detect and resolve security and code quality issues (/review), and 3) generating unit tests automatically and improving test coverage (/test) across the software development lifecycle in your preferred IDE or GitLab Duo with Amazon Q (in preview), which is one of the most popular enterprise DevOps platforms.

Get started with Amazon Q Developer agents for software development capabilities
To get started with all the new capabilities, you can install the latest Amazon Q IDE extension for your favorite IDEs. Sign in for the Free or Pro Tier of Amazon Q Developer, and open your project in your IDE. You can authenticate for the Free Tier with AWS Builder ID or for the Pro Tier with AWS IAM Identity Center.

1. Enhanced documentation in codebases
You can now generate comprehensive documentation, such as readmes and data flow diagrams about the codebase in your preferred IDE. With Amazon Q Developer handling the labor-intensive task of documentation, you can focus your efforts on designing and authoring code—all while maintaining quality based on software engineering best practices.

To start the documentation with your IDE, open the chat panel and type /doc.

Now you can create a README or update an existing README in your project. It will scan source files, create knowledge graph, summarize source files, and generation documents. When complete, check out the created REAME file and choose Accept to use this document in the code editor.

2. Supporting code reviews to detect and resolve code quality issues
You can identify and resolve a spectrum of code quality issues pertaining to code smells, anti-patterns, naming convention violations, potential bugs, logical errors, code duplication, poor documentation and security vulnerabilities, as well as AWS best practices across your IDE or GitLab repository.

This automated code review process empowers your development teams to save substantial time, improve productivity, and maintain consistency in code quality, ultimately enabling faster feature releases while adhering to security standards and best practices.

To start the code reviews with your IDE, open the chat panel and type /review.

Amazon Q Developer will review your project or a particular file you select and identify issues before code commit, provide a list of findings from where you can follow up with Amazon Q to find solution, and generate on-demand code fixes inline. When complete, check out the suggested code fixes for code issues and choose Accept Fix to apply the changes in the code editor.

3. Generating unit tests automatically and improving test coverage
You can automate the unit test process from identifying test cases to writing unit tests for your project files. Within unit tests, you can generate basic cases such as boundary conditions, null values, off-by-1 cases, and checking multiple input types.

To start the unit test workflow with your IDE, open the chat panel and type /test.

Amazon Q Developer will generate unit tests in your specific source file, place them into the relevant test file and self-debug test errors. When complete, choose View diff to check out the generated unit tests in the code editor. Then, you can accept or reject the generated unit tests.

Now available
Three new Amazon Q Developer agent capabilities for software development are now available in all AWS Regions where Amazon Q Developer is available.

To learn more, visit the Amazon Q Developer product page and the latest blog posts in the AWS DevOps & Developer Productivity Blog channel. My team also focuses on creating content on Amazon Q Developer that directly supports software developers’ jobs-to-be-done, enabled and enhanced by generative AI in the Amazon Q Developer Center and Community.aws.

Give new Amazon Q Developer agent capabilities a try in your favorite IDE with AWS Builder ID and send feedback to AWS re:Post for Amazon Q Developer or through your usual AWS Support contacts.

— Channy