News

New 'Amazon Q' AI Assistant vs. Amazon CodeWhisperer: What's the Diff?

• By David Ramel
• 11/30/2023

Cloud-native developers on the Amazon Web Services (AWS) cloud computing platform were greeted with a preview of a new generative AI assistant called Amazon Q during the company's ongoing re:Invent conference.

It's described as "a new generative artificial intelligence- (AI)-powered assistant designed for work that can be tailored to your business." Seeing as how AWS already offers Amazon CodeWhisperer, an "AI-powered productivity tool for the IDE and command line," there might be some confusion between the two. Here's the diff.

The upshot -- or tl;dr if you prefer -- is that Amazon Q actually is tied into Amazon CodeWhisper but expands on the latter's coding-specific functionality. For a longer summary, while both Amazon Q and CodeWhisperer are AI-powered tools from Amazon, they serve different purposes. Amazon Q is a broader enterprise AI assistant designed to interact across various data repositories and systems, whereas CodeWhisperer is more focused on software development, offering code generation and assistance within an IDE or code editor. Integration of Amazon Q with CodeWhisperer bridges the gap between these two functionalities, providing a comprehensive tool that assists in both general enterprise queries and specific software development tasks.

"Amazon CodeWhisperer generates code suggestions ranging from snippets to full functions in real time in the IDE based on your comments and existing code," the product's site states. "It also supports CLI completions and natural-language-to-bash translation in the command line."

In announcing Amazon Q this week, AWS explained how its abilities reach far beyond coding: "You can use Amazon Q to have conversations, solve problems, generate content, gain insights, and take action by connecting to your company's information repositories, code, data, and enterprise systems. Amazon Q provides immediate, relevant information and advice to employees to streamline tasks, accelerate decision-making and problem-solving, and help spark creativity and innovation at work."

Which is not to say Q doesn't help with coding -- it does.

A news release explained that: "Developers can use Amazon Q to explain specific programming logic by asking questions (e.g., 'Provide me with a description of what this application does and how it works.'), and Amazon Q will give details like which services the code uses and what different functions do (e.g., 'This application is building a basic support ticketing system using Python Flask and AWS Lambda.'), along with a description of the application's core capabilities, how they are implemented, and more. Amazon Q can also help developers debug, test, and optimize their code."

A Nov. 28 blog post explains much more about Q's developer functionality:

Application development is a journey. It involves a continuous cycle of researching, developing, deploying, optimizing, and maintaining. At each stage, there are many questions -- from figuring out the right AWS services to use, to troubleshooting issues in the application code.

Trained on 17 years of AWS knowledge and best practices, Amazon Q is designed to help you at each stage of development with a new experience for building applications on AWS. With Amazon Q, you minimize the time and effort you need to gain the knowledge required to answer AWS questions, explore new AWS capabilities, learn unfamiliar technologies, and architect solutions that fuel innovation.

So basically on the development side, Q offers a more interactive experience, allowing developers to have a conversation with the AI to understand their code better while helping with sundry other tasks. As a comparative example, the Q/CodeWhisperer situation is somewhat akin to Microsoft's development ecosystem in which the existing code-completion capabilities of IntelliSense (and later IntelliCode) were supplanted -- or supplemented -- by the original GitHub Copilot, which itself was then enhanced by the more interactive, conversational, generative abilities of Copilot Chat, based on advanced generative AI tech from OpenAI.

One development-specific Q offering is Amazon Q Code Transformation (Preview), which can be used to upgrade Java apps, for example.

However, as noted by AWS above, Q's reach extends into other areas to serve IT pros in addition to developers.

AWS documentation explains some capabilities of Q beyond coding:

• Tap into your company's knowledge base to get answers and guidance
• Understand how supply chain changes impact your operations
• Research solutions and learn about AWS best practices
• Quickly build dashboards and data stories
• Help your contact center agents respond to and solve customer issues

"Amazon Q can be tailored to your business by connecting it to company data, information, and systems, made simple with more than 40 built-in connectors," AWS explained. "Business users -- like marketers, project and program managers, and sales representatives, among others -- can have tailored conversations, solve problems, generate content, take actions, and more. Amazon Q is aware of which systems they can access, so they can ask detailed, nuanced questions and get tailored results that include only information they are authorized to see."

AWSInsider's Glady Rama explained more about that in the article, "Amazon Unveils Its Answer to Microsoft Copilot: 'Q'":

For business customers who want to use Q as a sort of employee knowledge hub, they can prime the solution on company data and not on the Internet at large. (Amazon also assures that it does not use private customers' data to train its AI models.) Organizations can block or filter specific topics and keywords, or limit what different groups of users can ask questions about.

The idea is that Q is "informed by a customer's information repositories, code, and enterprise systems" and "can personalize its interactions to each individual user based on an organization's existing identities, roles, and permissions."

Because Q is tied into CodeWhisperer, anyone using it must pay for the Amazon CodeWhisperer Professional tier. They must also install or update the latest AWS Toolkit.

Amazon Q feature development capability is currently in preview in the Visual Studio Code editor and the Amazon CodeCatalyst development service.