Introducing Q Developer: The Upgraded and Expanded Amazon CodeWhisperer

Pour one out for CodeWhisperer, Amazon’s AI-powered assistive coding tool. As of today, it’s kaput — sort of.

CodeWhisperer is now Q Developer, a part of Amazon’s Q family of business-oriented generative AI chatbots that also extends to the newly announced Q Business. Available through AWS, Q Developer helps with some of the tasks developers do in the course of their daily work, like debugging and upgrading apps, troubleshooting and performing security scans — much like CodeWhisperer did.

In an interview with TechCrunch, Doug Seven, GM and director of AI developer experiences at AWS, implied that CodeWhisperer was a bit of a branding fail. Third-party metrics reflect as much; even with a free tier, CodeWhisperer struggled to match the momentum of chief rival GitHub Copilot, which has over 1.8 million paying individual users and tens of thousands of corporate customers. Poor early impressions surely didn’t help.

“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,” Seven said. “You can think of Q Developer as the evolution of CodeWhisperer into something that’s much more broad.”

Q Developer has the capability to generate code, including SQL, which is widely used for the creation and management of databases. Additionally, it can test and help implement new code formulated through developer queries.

Similar to Copilot, customers have the ability to fine-tune Q Developer for their specific internal codebases to enhance the accuracy of the tool’s coding suggestions. Q Developer also provides a feature known as Agents, which can independently carry out tasks such as implementing features, code documentation, and code restructuring. This option was also offered by the now-obsolete CodeWhisperer.

Developers can make requests such as “create an ‘add to favorites’ button in my app”. Q Developer will analyze the app code, generate fresh code if required, create a systematic plan, and conduct tests on the code prior to implementing the proposed changes. Developers have the flexibility to review and amend the plan before Q Developer puts it into effect, coordinating steps and installing updates across the necessary files, code blocks, and test suites.

Q Developer also has a feature that sets up a development environment to process the code. “When it comes to feature development, Q Developer takes the entire code repository, creates a new branch, analyzes the repository, carries out the requested tasks, and then returns the modified code to the developer,” said Seven.

Image Credits: Amazon

Agents can also automate and manage code upgrading processes, according to Amazon, with conversions in Java live today (specifically Java 8 and 11 built using Apache Maven to Java version 17) and conversions in .NET arriving soon. “Q Developer analyses the code, identifying anything that needs an upgrade, and undertakes these changes before presenting it back to the developer for review and commitment,” Seven added.

In my view, Agents bear a lot of resemblance to GitHub’s Copilot Workspace, which similarly generates and puts into effect plans for bug fixes and fresh features in software. Interestingly, as with Workspace, I am not entirely convinced that this largely self-directed approach can address the problems inherent in AI-powered coding assistants.

An analysis of over 150 million lines of code committed to project repos over recent years by GitClear discovered that Copilot was leading to an increase in faulty code being added to codebases. Simultaneously, security researchers have cautioned that Copilot and similar tools can exaggerate existing bugs and security issues in software projects.

This isn’t surprising. AI-powered coding assistants seem impressive. But they’re trained on existing code, and their suggestions reflect patterns in other programmers’ work — work that can be seriously flawed. Assistants’ guesses create bugs that are often difficult to spot, especially when developers — who are adopting AI coding assistants in great numbers — defer to the assistants’ judgement.

In less risky territory beyond coding, Q Developer can help manage a company’s cloud infrastructure on AWS — or at least get them the info they need to do the managing themselves.

Q Developer can fulfill requests like “List all of my Lambda functions” and “list my resources residing in other AWS regions.” Currently in preview, the bot can also generate (but not execute) AWS Command Line Interface commands and answer AWS cost-related questions, such as “What were the top three highest-cost services in Q1?”

Amazon

So, what is the cost for these AI-based conveniences?

Q Developer can be utilized at no cost via the AWS Console, Slack and IDEs like Visual Studio Code, GitLab Duo, and JetBrains — although there are restrictions. The costless version doesn’t allow adjustments to custom libraries, packages, and APIs, and it automatically opts into a data gathering procedure. Additionally, it sets monthly limitations, including a maximum of five Agents tasks (such as implementing a feature) per month and 25 inquiries about AWS account resources per month. Surprisingly, Amazon chooses to limit the number of inquiries one can make about their own services.

Q Developer’s premium variant, known as Q Developer Pro, comes with a $19 monthly fee per user. It provides higher usage caps, tools to manage users and policies, single sign-on, and perhaps most crucially, IP indemnity.

Image Credits: Amazon

In many cases, the models underpinning code-generating services such as Q Developer are trained on code that’s copyrighted or under a restrictive license. Vendors argue that fair use defends them if the model was purposely or accidentally developed on copyrighted code — but there’s disagreement. GitHub and OpenAI are being sued in a class action lawsuit that alleges them of copyright infringement by letting Copilot to churn out licensed code snippets without acknowledgement.

Amazon asserts that it’ll shield Q Developer Pro clients against lawsuits alleging that the service violates a third party’s IP rights as long as they allow AWS to lead their defense and resolve “as AWS deems fit”.

Discover the pinnacle of WordPress auto blogging technology with AutomationTools.AI. Harnessing the power of cutting-edge AI algorithms, AutomationTools.AI emerges as the foremost solution for effortlessly curating content from RSS feeds directly to your WordPress platform. Say goodbye to manual content curation and hello to seamless automation, as this innovative tool streamlines the process, saving you time and effort. Stay ahead of the curve in content management and elevate your WordPress website with AutomationTools.AI—the ultimate choice for efficient, dynamic, and hassle-free auto blogging. Learn More