Amazon CodeWhisperer is now called Q Developer and is expanding its functions
Today marks the end of an era for CodeWhisperer, Amazon’s AI-powered assistive coding tool. However, it’s not a complete farewell, as CodeWhisperer has undergone a transformation and emerged as Q Developer, now part of Amazon’s Q family of business-oriented generative AI chatbots, alongside the newly introduced Q Business. Hosted on AWS, Q Developer continues to support developers in their daily tasks, offering assistance with debugging, app upgrades, troubleshooting, and security scans, much like its predecessor, CodeWhisperer.
In an interview with TechCrunch, Doug Seven, GM and director of AI developer experiences at AWS, suggested that CodeWhisperer faced challenges in terms of branding. Despite offering a free tier, CodeWhisperer struggled to gain traction, particularly when compared to its primary competitor, GitHub Copilot, which boasts over 1.8 million paying individual users and thousands of corporate customers. Seven noted that early perceptions may have contributed to CodeWhisperer’s struggles.
According to Seven, Q Developer represents the evolution of CodeWhisperer, with a broader scope and capabilities. Q Developer can now generate code in SQL, a vital programming language for database creation and management. Additionally, it facilitates code testing, transformation, and implementation based on developer queries, catering to a wider range of use cases.
While CodeWhisperer bids adieu, Q Developer emerges as a reinvigorated and versatile tool, poised to meet the evolving needs of developers across various domains.
Q Developer offers a functionality akin to Copilot, allowing customers to refine its recommendations by fine-tuning the tool on their internal codebases—a feature also available in the now-deprecated Code Whisperer. Additionally, through a feature called Agents, Q Developer can autonomously execute tasks such as implementing features, documenting, and refactoring code.
Upon receiving a request like “create an ‘add to favorites’ button in my app,” Q Developer undertakes a comprehensive analysis of the app’s code. If necessary, it generates new code and formulates a step-by-step plan. Before executing the proposed changes, Q Developer conducts tests to ensure the integrity of the code. Developers have the opportunity to review and refine the plan before Q Developer proceeds with implementation. It seamlessly connects steps and applies updates across relevant files, code blocks, and test suites.
Behind the scenes, Q Developer leverages a development environment to carry out the requested tasks. For instance, in feature development, it initiates a branch of the entire code repository, performs the necessary analysis and modifications, and then returns the code changes to the developer for review and integration. This approach streamlines the development process and enhances collaboration between developers and the Q Developer tool.
Image Credits: Amazon
Amazon’s Agents feature within Q Developer offers the capability to automate and manage code upgrading processes. Presently, it supports Java conversions, including Java 8 and 11 built using Apache Maven, to Java version 17, with .NET conversions anticipated soon. Q Developer analyzes the code, identifies areas requiring upgrades, and implements the necessary changes, providing developers with reviewed code for their final confirmation and commitment.
Agents bears resemblance to GitHub’s Copilot Workspace, which similarly generates and executes plans for bug fixes and feature enhancements in software. However, concerns persist regarding the efficacy of such autonomous approaches in resolving issues associated with AI-powered coding assistants.
An analysis of over 150 million lines of code by GitClear revealed that Copilot contributed to an increase in erroneous code being incorporated into codebases. Additionally, security researchers caution that tools like Copilot can potentially exacerbate existing bugs and security vulnerabilities in software projects. These AI assistants, while impressive, are trained on existing code, which may contain flaws. Consequently, their suggestions may inadvertently introduce bugs that are challenging to detect, especially as developers increasingly rely on their judgments.
Despite these challenges, Q Developer extends its utility beyond coding tasks to assist in managing a company’s cloud infrastructure on AWS. Through Q Developer, users can request information such as listing all Lambda functions, identifying resources in other AWS regions, and obtaining insights into AWS cost-related queries, including top-cost services in a specified timeframe. Currently available in preview, Q Developer can also generate AWS Command Line Interface commands, although it does not execute them.
Image Credits: Amazon
So how much do these generative AI conveniences cost?
Q Developer is accessible for free through various platforms including the AWS Console, Slack, and IDEs such as Visual Studio Code, GitLab Duo, and JetBrains. However, the free version comes with certain limitations. Users are unable to fine-tune the tool to custom libraries, packages, and APIs, and are automatically enrolled in a data collection program. Moreover, the free version imposes monthly caps, including a maximum of five Agents tasks (e.g., implementing a feature) per month and 25 queries about AWS account resources per month. It’s worth noting the irony of Amazon placing restrictions on inquiries about its own services.
For users seeking enhanced capabilities, the premium version, Q Developer Pro, is available at $19 per month per user. This upgrade offers higher usage limits, tools for user and policy management, single sign-on functionality, and importantly, IP indemnity protection. With Q Developer Pro, users can leverage additional features and functionalities while ensuring greater security and compliance with their development processes.
Image Credits: Amazon
The models powering code-generating services like Q Developer often rely on code that is copyrighted or subject to restrictive licenses. While vendors argue that fair use protects them, disagreements persist regarding the extent of this protection. GitHub and OpenAI, for instance, face a class action lawsuit alleging that Copilot violates copyright by reproducing licensed code snippets without attribution.
In response to potential legal challenges, Amazon assures Q Developer Pro customers that it will defend them against claims of IP infringement. However, this defense is contingent upon customers allowing AWS to control their defense and settle matters as deemed appropriate by AWS. This approach aims to mitigate legal risks for Q Developer Pro users by transferring responsibility for legal proceedings and settlements to AWS.