Say goodbye to CodeWhisperer, Amazon’s AI-driven coding assistant. As of today, it has been rebranded and transformed into Q Developer, part of Amazon’s expanding Q suite of business-focused generative AI chatbots, which now includes the newly launched Q Business. Accessible through AWS, Q Developer assists developers with everyday tasks, notably debugging, upgrading applications, troubleshooting, and conducting security scans—similar to the functionalities offered by CodeWhisperer.
In a recent interview, Doug Seven, General Manager and Director of AI Developer Experiences at AWS, suggested that CodeWhisperer may have suffered from branding challenges. This is reflected in third-party metrics; even with a free tier, CodeWhisperer failed to gain traction against its main competitor, GitHub Copilot, which boasts over 1.8 million paid users and numerous corporate clients. “CodeWhisperer was our starting point for code generation, but we needed a name — and brand — that resonates with a broader audience,” Seven stated. “Think of Q Developer as the evolution of CodeWhisperer into a more comprehensive platform.”
Q Developer is now capable of generating SQL code, a popular programming language for database management, while also offering testing assistance and helping with the transformation and implementation of newly conceptualized code from developer queries. Like Copilot, users can refine Q Developer’s suggestions by integrating it with their internal codebases to enhance the relevance of its programming recommendations. Additionally, thanks to a feature called Agents, Q Developer can autonomously execute tasks like implementing features and managing code restructuring.
For example, if you instruct Q Developer to “create an ‘add to favorites’ button in my app,” it will evaluate the app’s code, generate any necessary new code, devise a step-by-step plan, and test the code before applying the changes. Developers can review and modify the plan before Q implements it, ensuring smooth updates across relevant files, code segments, and testing frameworks.
“What goes on behind the scenes is that Q Developer sets up a development environment to work with the code,” explained Seven. “For feature development, it creates a branch from the entire code repository, analyzes it, performs the requested work, and then returns the code changes to the developer.”
Agents can also automate and oversee the code upgrade process, with live Java conversions currently available (specifically from Java 8 and 11 using Apache Maven to Java version 17), and .NET conversions on the way. “Q Developer assesses the code for anything needing an upgrade and implements those changes before sending it back to the developer for review and approval,” Seven added.
However, some parallels can be drawn between Agents and GitHub’s Copilot Workspace, which similarly generates and executes strategies for bug fixes and new feature implementations. There’s a lingering concern about whether this advanced, autonomous approach can truly resolve the challenges surrounding AI-powered code assistance.
Research analyzing over 150 million lines of code committed to project repositories over recent years by GitClear found that Copilot actually led to an increase in erroneous code being added to codebases. Security experts have also cautioned that tools like Copilot can amplify existing bugs and security vulnerabilities in software projects.
This isn’t entirely surprising. Although AI-driven coding assistants appear impressive, they draw on existing code which often includes flawed patterns from other developers' work. Such assistants can inadvertently introduce bugs that are challenging to detect, especially when developers, now progressively adopting AI tools, lean on these assistants for judgment.
Beyond coding, Q Developer also aids in managing cloud infrastructure on AWS, supplying users with vital information to facilitate their management tasks. It can handle queries such as “List all my Lambda functions” and “List my resources in other AWS regions.” Currently in preview, the bot can generate (but not execute) AWS Command Line Interface commands, as well as answer AWS cost-related inquiries, like “What were the top three highest-cost services in Q1?”
So, what are the costs associated with these generative AI tools?
Q Developer is available for free through the AWS Console, Slack, and IDEs including Visual Studio Code, GitLab Duo, and JetBrains, albeit with some limitations. The free version does not allow fine-tuning with custom libraries or APIs and opts users into a data collection program by default. It also imposes monthly usage caps—limited to five Agents tasks (e.g., implementing a feature) and 25 resource queries about AWS account resources.
The premium offering, Q Developer Pro, comes at $19 per month per user, providing elevated usage limits, enhanced management tools, single sign-on capabilities, and importantly, IP indemnity.
Many models that underpin code-generating services like Q Developer have been trained on copyrighted or restricted code. While vendors argue that fair use protects them, not everyone is convinced. GitHub and OpenAI currently face a class-action lawsuit for allegedly violating copyright law by allowing Copilot to reproduce licensed code snippets without attribution.
Amazon has stated that it will provide defense against claims alleging that Q Developer Pro infringes on third-party intellectual property rights, provided customers allow AWS control over their defense strategy and settlements.
Ranking
