AWS Enhances Amazon Q Developer with AI-Powered Features for Comprehensive Software Development Lifecycle

AWS wants Amazon Q to become your buddy for the entire software development lifecycle

At its re:Invent conference, AWS today announced a series of updates to Q Developer, its coding assistant platform that competes with the likes of GitHub Copilot. The focus here is on going beyond code completion and to help developers with a wider range of routine tasks involved in the end-to-end software lifecycle. The service, which you may still remember under its previous name of 'CodeWhisperer,' is part of AWS's overall Amazon Q generative AI platform, which also includes Q Business (and which is also getting a slew of updates today). "What developers need is they want to actually have Q be the buddy to solve some of the undifferentiated heavy lifting so that they can actually have more freedom to innovate," Swaminathan 'Swami' Sivasubramanian, AWS' VP of AI and Data, told me. "So that's why having an assistant -- or buddy -- that helps them do things faster, more streamlined, is such an important thing, and that's why we're focused on it in a big way." Managing the end-to-end software lifecycle Sivasubramanian told me that he believes what differentiates Q Developer from competing platforms is its focus on the entire software development lifecycle. So far that meant helping developers troubleshoot issues and perform multi-step tasks to fix them (or built entirely new apps), as well as scan the code for security vulnerabilities. At this re:Invent, the company is taking this a step further. Q can now, for example, automatically generate unit tests, for example. But what's maybe even more important is that it can now also do the one thing that many developers hate the most: write and maintain the documentation for that code. To complete this cycle, Q can now generate a first code review when developers check in their code. "In Amazon, we have this rule that no code ever gets checked in without a code review," Sivasubramanian said. "So if you don't do a code review, then you cannot check in code. But not many enterprises actually have either enough senior engineers to review or the senior engineer says: 'I can't deal with so many reviews. Can somebody first review it before we do so?' Q we will streamline the code review process by being the first line of reviewer and takes care of the automatically checking code quality, security vulnerabilities and so forth." Then, once the code is in production, a new operations agent for Q can now automatically pull in data from AWS CloudWatch, the company's monitoring service, and immediatly start investigating when an alarm goes off. "It utilizes the [knowlege it has about an] organization's AWS resources and then it sifts through hundreds of data points across various resources sitting in CloudWatch. Then, after analyzing it, Q comes up with potential hypothesis for the root cause and then it guides the users through how to fix it," Sivasubramanian explained. All you wanted for Christmas was help with your Cobol and .NET migrations, right? For those enterprises with older codebases, transitioning to the cloud often involves rewriting a lot of their existing code. One of the earliest differentating features of Amazon Q Developer was its agent for code transformation. At the time, the focus of this agent was to on moderizing older Java apps. Today, the team is expanding this by also helping developer update their older .NET-based applications from Windows to Linux. And while this may at first seem like a curiosity, AWS is also launching an agent for modernizing COBOL mainframe applications. A lot of large enterprises still rely on this old code, after all, which few developers know to work with today. These are very complex migrations, Sivasubramanian stressed, and so the goal here is not to simply translate the existing code 1:1. "Our goal is not to actually just like fully COBOL project in, code out," he said. "The reality is, these projects are inherently extremely complex. You need to have a human in the loop to leverage it, but I've heard customers say, 'Hey, this takes multiple years and customers have explicitly told us this is a game changer and would significantly drop that timeline." Sivasubramanian noted that while there is less COBOL code to train models to automate the code migration, the team was able to leverage AWS' overall experience in modernizing mainframe applications, as well as more traditional methods for code translation. "Taking code from one language to another one arguably is the easy part," he said. "But the harder part is: how do you know you got it right? And how do you even know what the code does? And then the challenge in these [codebases] is they are usually poorly documented and dependencies are not well understood. So what we have built is really extremely innovative, and [the system] also understands, at a project level, what are the objectives of each of the module, and then plans out and creates a migration planning timeline to actually generate the code, and then generate the test -- and bringing humans in the loop to see how you validate it."

AWS enhances Q Developer AI assistant to reduce tedium, accelerate work - SiliconANGLE

AWS enhances Q Developer AI assistant to reduce tedium, accelerate work To make the lives of developers easier and reduce their workloads, Amazon Web Services Inc. released several updates to the company's artificial intelligence software development assistant, Amazon Q Developer. New capabilities announced today at AWS re:Invent included AI agents to automate unit testing, writing documentation and producing code reviews to assist developers in building software faster throughout the entire development lifecycle. Q Developer will also receive the capability to assist with operational issues by assisting with investigating and fixing issues. The AI assistant is also gaining capabilities to autonomously help with the heavy lifting during application migration projects. Modernizing applications and operating systems can be time-consuming and labor-intensive, which involves code analysis, documentation, planning and major changes to entire systems taking time and energy away from development. "Amazon Q Developer is fundamentally transforming how developers work and can speed up a variety of software development tasks by up to 80%, providing the highest reported code acceptance rate of any coding assistant that suggests multi-line code, code security scanning that outperforms leading publicly benchmarkable tools, and high-performing AI agents that autonomously reason and iterate to achieve complex goals," said Deepak Singh, vice president of next-generation developer experience at AWS. Making reliable code depends on having solid tests that can catch potential issues early. However, writing tests is a labor-intensive process that involves going back over already written code. Amazon said generating unit tests for code is now as simple as using the generative AI assistant to produce it after they complete their code segments so they can move on and focus on coding instead of preparing tests. Developers spend a certain amount of time "proofreading" each other's code by reviewing it to make sure that it fits standards for quality, style and security. After preparing a code revision or functionality, a developer can wait hours or days for another developer to become available to review their code and then wait more time for feedback on a revision. To help break this cycle, Q Developer now helps automate the detection of code-quality issues earlier to help save developers time on future reviews. With the assistant running, developers get feedback sooner about their code standards when they need it, helping them maintain better code quality based on best practices. The assistant can supply recommendations on how to fix the code to maintain standards after every line of code and with every merge request. This helps produce better code before peer review and reduces the number of rollbacks or revisions. Q Developer now automatically keeps up with documenting code, something that often breaks developers out of the flow of producing code. After writing and preparing code, developers often have to stop and explain how it works. However, the longer a project goes on, the more complex it gets and the more pieces are interconnected. Now, Q can update disparate pieces of documentation so that they remain up-to-date without the developer having to hunt them down and correct them. With correct and understandable documentation, updated as coders go about their work, this means that it becomes easier to understand code when scanning it for the first time or refreshing knowledge of it. Q Developer presents its proposed changes to documentation so developers can see that updates are accurate as they go, allowing them to control the maintenance of documentation. After all the code writing is completed and an application is in production, problems can still crop up that need to be fixed in code. When issues happen, development and operations teams need to move as quickly as possible to get the application working as it should so that customers can get back to using it as it was intended. Traditionally, if something goes wrong in an application, the operations team investigates the issue and passes along the errors and telemetry to development. The development team then attempts to discover and repeat the issue, or bug, on a virtual server so that the problem can be fixed and pushed out to production. This is a process that can involve sifting through many lines of data and code to determine what went wrong and how to fix it. With access to the codebase and information about the health of the application and monitoring, Q can now quickly sift through hundreds of thousands of data points between services to begin investigating the moment an issue is discovered. The AI assistant can then use this to help form an analysis of a potential root cause for both operations and development to issue guidance on how to fix it. Amazon added that where possible, Q will access routine procedures such as runbooks and, if permitted, will automatically execute them. The potential benefit is that Q Developer will take on the hard, tedious work of the investigation so that operations can get to the cause faster and the development team can address a fix sooner. Many organizations have legacy applications that exist on old hardware or operating systems that need to be moved to more modern systems, but this can be laborious and tedious work. Today, Amazon announced a new capability for Q Developer that will provide transformation capabilities to make these projects easier by autonomously analyzing source code, generating new code, testing it and executing the change for the customer once approved. "We are combining Amazon Q Developer with our nearly two decades of experience helping organizations migrate and modernize their legacy workloads on AWS to accelerate and simplify large-scale transformations," said Mai-Lan Tomsen Bukovec, vice president of technology at AWS. "This is a game-changer for customers and partners looking to move off Windows .NET, VMware and mainframes." Amazon initially integrated the Java transformation capability of Q Developer internally to migrate tens of thousands of production applications from an older version of Java to Java 17. The company said the effort saved more than 4,500 years of development work and $260 million in annual cost savings. The company added that customers using Q can modernize Windows .NET applications to the Linux operating system up to four times faster than traditional methods and reduce licensing costs by up to 40%. Amazon said using the new capability, customers can shift VMware workloads from data centers to AWS faster. Amazon Q's agents can automatically identify dependencies to accomplish what Amazon said can take weeks of manual work to convert on-premises networking configurations into AWS configurations in a matter of hours. Amazon Q can also assist with moving off mainframes, starting with IBM z/OS mainframe systems. Now Amazon partners and customers can collaborate using Q to reduce costs by having an expert assist them with a range of tasks including generating documentation and preparing applications. For example, Amazon Q can work with developers to document thousands of COBOL programs, a truly tedious and nearly impossible task, and prepare their logic and business rules for the move to AWS. The new capabilities to assist with migrating large-scale Windows .NET, VMware and mainframe projects will be available through a new Amazon Q Developer web application. Amazon said this will be designed to help customers collaborate on hundreds of complex transformation projects simultaneously by giving them a place to review them together easily. The VMware and mainframe modernization capabilities are only accessible through the new web interface, while developers can also perform Windows .NET transformations in their development editors.