Search the Community

AWS IAM Identity Center administrators now have an option to extend the session duration for Amazon CodeWhisperer separately from the session durations of other IAM Identity Center integrated applications and the AWS access portal. Users of Amazon CodeWhisperer can work in the integrated development environment (IDE) for 90 days without being asked to re-authenticate by CodeWhisperer. View the full article

Amazon CodeWhisperer is a revolutionary artificial intelligence (AI)-powered productivity tool that improves developer productivity and can serve as an accelerated learning path for cloud computing. Amazon CodeWhisperer uses machine learning (ML) to provide intelligent code suggestions in an integrated development environment (IDE). Amazon CodeWhisperer is trained on billions of lines of Amazon and publicly available code. It has built-in security scans, provides code suggestions to remediate any issues it identifies, and makes it easy for developers to deploy AWS services that meet AWS best practices. Whether you are a new cloud architect or an experienced developer, Amazon CodeWhisperer can increase your cloud fluency by generating code examples, API references, and infrastructure-as-code (IaC) templates. In this blog, we’ll explore three practical ways developers and cloud architects can use Amazon CodeWhisperer as an educational catalyst in their cloud learning journey. 1. Generate templates for infrastructure-as-code When starting out with AWS, many people will manually deploy resources using the AWS Management Console. However, as cloud proficiency grows, the best practice is to adopt IaC approaches using services like AWS CloudFormation or Terraform. IaC allows you to deploy your entire AWS infrastructure via declarative code template, enabling repeatability and scalability in a controlled manner with less room for error. These templates serve as blueprints and are a great way to learn how to deploy AWS resources. → Using Amazon CodeWhisperer Amazon CodeWhisperer can help you overcome the IaC learning curve by synthesizing IaC templates based on your instructions and previous code context. In the example below, I provided a high-level comment instructing Amazon CodeWhisperer to create an AWS CloudFormation template. Amazon CodeWhisperer generated the AWSTemplateFormatVersion section, which is the first step in creating a CloudFormation template. Next, I gave Amazon CodeWhisperer additional instructions to create a Virtual Private Cloud (VPC), Subnet, and Elastic Compute Cloud (EC2) instance. Amazon CodeWhisperer knows this is a CloudFormation template based on the AWSTemplateFormatVersion line and generates the code, in grey, needed to accomplish the instructions. To accept, simply hit tab and the code is placed into the IDE. Amazon CodeWhisperer speeds up the development process by generating code for you so you don’t have to manually look up syntax, documentation, and resources specifications. If you’re new to cloud, you can use Amazon CodeWhisperer to quickly understand the format of AWS CloudFormation templates and method to deploy AWS services programmatically. This synthesized starting point can be helpful when learning a new IaC language or when you need to quickly learn about cloud environments. Amazon CodeWhisperer gives you a head start based on the specifications and instructions you provide. 2. Learn about your organization’s code base When you join a new team or start work on a new project, it can be challenging to learn the intricacies of the organization’s coding and cloud architecting best practices. Amazon CodeWhisperer can be customized to generate recommendations based on an organization’s internal libraries and architectural patterns. This enables Amazon CodeWhisperer to recommend more relevant code, onboard developers faster, and help you get up to speed on AWS cloud services. → Using Amazon CodeWhisperer Amazon CodeWhisperer can be connected to your organization’s GitHub, AWS CodeCommit, or other Git repositories. Amazon CodeWhisperer will then generate code suggestions in the context of your organization, helping you quickly learn the organization’s coding style and architectural patterns without having to go through documentation and different development projects. Further, Amazon CodeWhisperer can be a continuous learning tool for seasoned developers and architects. Organizations can add new standards, libraries, and frameworks to their codebase, and Amazon CodeWhisperer will incorporate it into recommendations. This provides an avenue for veteran developers to stay up-to-date on organizational changes and technologies without having to read announcements or change documentation. 3. Integrate Amazon CodeWhisperer with Amazon Q to further your learning Sometimes, you need more in-depth explanations or guidance than the code suggested by Amazon CodeWhisperer. For this, Amazon CodeWhisperer can be integrated with Amazon Q, an interactive, generative AI-powered assistant available in the IDE. You can ask Amazon Q to explain, refactor, fix, or optimize code right in your IDE, giving you deeper insights so you learn more about the code being recommended. Going back to our first example, we can highlight and right click on the code generated, requesting Amazon Q to explain the code (right side of image below). This opens the Amazon Q chatbot (left side of image), explaining the highlighted code. The integration between Amazon CodeWhisperer and Amazon Q creates a loop of code generation and knowledge acquisition, allowing developers to continuously upskill on cloud while increasing their coding productivity. Build your knowledge of Amazon CodeWhisperer To learn more about Amazon CodeWhisperer, check out the free 30-minute Amazon CodeWhisperer – Getting Started course on AWS Skill Builder, our online learning center. In the course, you’ll learn the key features of Amazon CodeWhisperer and how to install, configure, and start using Amazon CodeWhisperer in your preferred IDE. Amazon CodeWhisperer is available in Visual Studio Code, JetBrains IDEs, AWS Cloud9, AWS Lambda, JupterLab, and more. You can then get hands-on via the AWS Jam, Build using Amazon CodeWhisperer, where you’ll learn how to effectively tackle time-consuming coding tasks and maximize your productivity. This AWS Jam contains seven engaging challenges and can be completed at your own pace. Take advantage of the 7-day free trial of AWS Skill Builder subscription to access this Jam for free. Conclusion Amazon CodeWhisperer is a powerful AI tool that can enhance the way developers and cloud architects learn about AWS and their organization’s application development process. You can use Amazon CodeWhisperer’s code synthesis, knowledge of your organization’s code base, and integration with Amazon Q to learn about AWS, all while building build cloud-native applications. Dive in and let Amazon CodeWhisperer guide your cloud education! This blog was written with minimal assistance from generative AI tools: Claude (2023). Used to augment and improve the syntax and content of this blog. Anthropic AI assistant. https://www.anthropic.com View the full article

At re:Invent in 2023, AWS announced Infrastructure as Code (IaC) support for Amazon CodeWhisperer. CodeWhisperer is an AI-powered productivity tool for the IDE and command line that helps software developers to quickly and efficiently create cloud applications to run on AWS. Languages currently supported for IaC are YAML and JSON for AWS CloudFormation, Typescript and Python for AWS CDK, and HCL for HashiCorp Terraform. In addition to providing code recommendations in the editor, CodeWhisperer also features a security scanner that alerts the developer to potentially insecure infrastructure code, and offers suggested fixes than can be applied with a single click. In this post, we will walk you through some common scenarios and show you how to get the most out of CodeWhisperer in the IDE. CodeWhisperer is supported by several IDEs, such as Visual Studio Code and JetBrains. For the purposes of this post, we’ll focus on Visual Studio Code. There are a few things that you need to follow along with the examples, listed in the prerequisites section below. Prerequisites An AWS Builder ID or an AWS Identity Center login controlled by your organization A supported IDE, like Visual Studio Code The AWS Toolkit IDE extension Authenticate and Connect CloudFormation Now that you have the toolkit configured, open a new source file with the yaml extension. Since YAML files can represent a wide variety of different configuration file types, it helps to add the AWSTemplateFormatVersion: '2010-09-09' header to the file to let CodeWhisperer know that you are editing a CloudFormation file. Just typing the first few characters of that header is likely to result in a recommendation from CodeWhisperer. Press TAB to accept recommendations and Escape to ignore them. AWSTemplateFormatVersion header If you have a good idea about the various resources you want to include in your template, include them in a top level Description field. This will help CodeWhisperer to understand the relationships between the resources you will create in the file. In the example below, we describe the stack we want as a “VPC with public and private subnets”. You can be more descriptive if you want, using a multi-line YAML string to add more specific details about the resources you want to create. Creating a CloudFormation template with a description After accepting that recommendation for the parameters, you can continue to create resources. Creating CloudFormation resources You can also trigger recommendations with inline comments and descriptive logical IDs if you want to create one resource at a time. The more code you have in the file, the more CodeWhisperer will understand from context what you are trying to achieve. CDK It’s also possible to create CDK code using CodeWhisperer. In the example below, we started with a CDK project using cdk init, wrote a few lines of code to create a VPC in a TypeScript file, and CodeWhisperer proposed some code suggestions using what we started to write. After accepting the suggestion, it is possible to customize the code to fit your needs. CodeWhisperer will learn from your coding style and make more precise suggestions as you add more code to the project. Create a CDK stack You can choose whether you want to get suggestions that include code with references with the professional version of CodeWhisperer. If you choose to get the references, you can find them in the Code Reference Log. These references let you know when the code recommendation was a near exact match for code in an open source repository, allowing you to inspect the license and decide if you want to use that code or not. References Terraform HCL After a close collaboration between teams at Hashicorp and AWS, Terraform HashiCorp Configuration Language (HCL) is also supported by CodeWhisperer. CodeWhisperer recommendations are triggered by comments in the file. In this example, we repeat a prompt that is similar to what we used with CloudFormation and CDK. Terraform code suggestion Security Scanner In addition to CodeWhisperer recommendations, the toolkit configuration also includes a built in security scanner. Considering that the resulting code can be edited and combined with other preexisting code, it’s good practice to scan the final result to see if there are any best-practice security recommendations that can be applied. Expand the CodeWhisperer section of the AWS Toolkit to see the “Run Security Scan” button. Click it to initiate a scan, which might take up to a minute to run. In the example below, we defined an S3 bucket that can be read by anyone on the internet. Security scanner Once the security scan completes, the code with issues is underlined and each suggestion is added to the ‘Problems’ tab. Click on any of those to get more details. Scan results CodeWhisperer provides a clickable link to get more information about the vulnerability, and what you can do to fix it. Scanner Link Conclusion The integration of generative AI tools like Amazon CodeWhisperer are transforming the landscape of cloud application development. By supporting Infrastructure as Code (IaC) languages such as CloudFormation, CDK, and Terraform HCL, CodeWhisperer is expanding its reach beyond traditional development roles. This advancement is pivotal in merging runtime and infrastructure code into a cohesive unit, significantly enhancing productivity and collaboration in the development process. The inclusion of IaC enables a broader range of professionals, especially Site Reliability Engineers (SREs), to actively engage in application development, automating and optimizing infrastructure management tasks more efficiently. CodeWhisperer’s capability to perform security scans on the generated code aligns with the critical objectives of system reliability and security, essential for both developers and SREs. By providing insights into security best practices, CodeWhisperer enables robust and secure infrastructure management on the AWS cloud. This makes CodeWhisperer a valuable tool not just for developers, but as a comprehensive solution that bridges different technical disciplines, fostering a collaborative environment for innovation in cloud-based solutions. Bio Eric Beard is a Solutions Architect at AWS specializing in DevOps, CI/CD, and Infrastructure as Code, the author of the AWS Sysops Cookbook, and an editor for the AWS DevOps blog channel. When he’s not helping customers to design Well-Architected systems on AWS, he is usually playing tennis or watching tennis. Amar Meriche is a Sr Technical Account Manager at AWS in Paris. He helps his customers improve their operational posture through advocacy and guidance, and is an active member of the DevOps and IaC community at AWS. He’s passionate about helping customers use the various IaC tools available at AWS following best practices. View the full article