Amazon has folded CodeWhisperer into a broader developer product called Q Developer, moving the AI coding assistant under the company’s Q family of business-oriented generative AI chatbots. The shift keeps the core idea of AI help for software work, but expands the product’s role across coding, testing, app upgrades, security scans and AWS infrastructure support.
The change also signals that Amazon wants Q Developer to compete in a market where GitHub Copilot has already built strong momentum. The result is a tool that still writes and reviews code, but is now positioned as a more general assistant for developers working inside AWS and common development environments.
From CodeWhisperer to Q Developer
CodeWhisperer was Amazon’s AI-powered assistive coding tool. It has now become Q Developer, alongside the newly announced Q Business in Amazon’s Q product family.
Doug Seven, GM and director of AI developer experiences at AWS, told TechCrunch that the earlier name no longer fit the wider product Amazon wanted to build. He said, “CodeWhisperer is where we got started [with code generation], but we really wanted to have a brand — and name — that fit a wider set of use cases.”
That wider scope matters. Q Developer can still help with everyday developer tasks such as debugging, upgrading apps, troubleshooting and running security scans. But Amazon is also giving it capabilities that go beyond simple code completion.
Competition is part of the backdrop. The source notes that CodeWhisperer struggled to match the momentum of GitHub Copilot, despite having a free tier. GitHub Copilot has over 1.8 million paying individual users and tens of thousands of corporate customers.
What Q Developer can do
Q Developer can generate code, including SQL, and it can test code as well. It can also help transform and implement new code ideas based on developer queries.
Customers can fine-tune Q Developer on their internal codebases, which is intended to make its programming recommendations more relevant to a company’s own libraries, packages and APIs. CodeWhisperer also offered this option before it was deprecated.
The larger change is a capability called Agents. With Agents, Q Developer can perform more autonomous work, including implementing features, documenting code and refactoring code.
For example, if a developer asks Q Developer to create an add to favorites button in an app, the tool can analyze the app code, generate new code if needed, create a step-by-step plan and test the code before making proposed changes. Developers can review the plan and iterate on it before Q Developer applies updates across the necessary files, code blocks and test suites.
Seven described the process this way: “What happens behind the scenes is, Q Developer actually spins up a development environment to work on the code.” He added that Q Developer takes the repository, creates a branch, analyzes it, does the requested work and returns code changes to the developer.
Agents bring automation to upgrades
Agents are also meant to automate code upgrades. Amazon says Java conversions are live today, specifically for Java 8 and 11 built using Apache Maven to Java version 17. .NET conversions are coming soon.
In this workflow, Q Developer analyzes the code, looks for anything that needs to be upgraded and makes the required changes before sending the result back for developer review and commit.
This places Q Developer near the same category as GitHub’s Copilot Workspace, which also generates and implements plans for bug fixes and new features. The practical promise is clear: developers could hand off structured, multi-step work that normally touches several files and tests.
But the source also raises an important caution. More autonomous coding assistants can still create problems when their suggestions are wrong, incomplete or based on flawed patterns from existing code.
The risk behind AI coding help
AI coding assistants can look impressive because they generate plausible code quickly. The problem is that they are trained on existing code, and existing code can contain bugs, insecure patterns and other weaknesses.
The source points to an analysis by GitClear of over 150 million lines of code committed to project repos over the past several years. That analysis found that Copilot was resulting in more mistaken code being pushed to codebases.
Security researchers have also warned that Copilot and similar tools can amplify existing bugs and security issues in software projects. That concern applies directly to the kind of automated work Q Developer is designed to handle.
For developers and engineering teams, the core lesson is straightforward: Q Developer may reduce manual work, but review still matters. A tool that can generate a plan, branch a repository, edit code and run tests is useful only if the human review step remains serious.
AWS management, pricing and IP protection
Q Developer is not limited to writing code. It can also help manage cloud infrastructure on AWS, or at least help users find the information they need to manage it themselves.
It can answer requests such as listing all Lambda functions or listing resources in other AWS regions. In preview, the bot can generate, but not execute, AWS Command Line Interface commands. It can also answer AWS cost-related questions, including identifying the top three highest-cost services in Q1.
Q Developer is available for free in the AWS Console, Slack and IDEs such as Visual Studio Code, GitLab Duo and JetBrains. The free version has limits. It does not allow fine-tuning to custom libraries, packages and APIs, opts users into a data collection scheme by default and includes monthly caps.
Those caps include a maximum of five Agents tasks per month and 25 queries about AWS account resources per month.
Q Developer Pro costs $19 per month per user. It adds higher usage limits, tools to manage users and policies, single sign-on and IP indemnity.
That last point is significant because code-generating services can be trained on code that is copyrighted or under restrictive licenses. GitHub and OpenAI are being sued in a class action motion that accuses them of violating copyright by allowing Copilot to regurgitate licensed code snippets without providing credit.
Amazon says it will defend Q Developer Pro customers against claims alleging that the service infringes on a third party’s IP rights, as long as they let AWS control the defense and settle “as AWS deems appropriate.”
Q Developer is therefore more than a renamed CodeWhisperer. It is Amazon’s attempt to package code generation, autonomous development tasks, AWS assistance and enterprise protections into one developer-focused AI product.