How Accenture is using Amazon CodeWhisperer to improve developer productivity

Amazon CodeWhisperer is an AI coding companion that helps improve developer productivity by generating code recommendations based on their natural language feedback and code in the integrated development environment (IDE). CodeWhisperer speeds up the completion of coding tasks by reducing context switches between the IDE and documentation or developer forums. With CodeWhisperer’s real-time code recommendations, you can stay focused in the IDE and finish your coding tasks faster.

CodeWhisperer is powered by a large language model (LLM) that is trained on billions of lines of code and as a result has learned to write code in 15 programming languages. You can only write a comment that describes a specific task in plain English, such as “upload a file to S3”. From this, CodeWhisperer automatically determines which cloud services and public libraries are best suited for the specified task, creates the specific code on the fly, and recommends the generated code snippets directly in the IDE. Plus, CodeWhisperer seamlessly integrates with your Visual Studio code and JetBrains IDEs so you can stay focused and never leave the IDE. At the time of writing, CodeWhisperer supports Java, Python, JavaScript, TypeScript, C#, Go, Ruby, Rust, Scala, Kotlin, PHP, C, C++, Shell, and SQL.

In this post, we illustrate how Accenture uses CodeWhisperer in practice to improve developer productivity.

“Accenture is using Amazon CodeWhisperer to accelerate coding as part of our software engineering best practices initiative on our Velocity platform,” says Balakrishnan Viswanathan, senior director of Technology Architecture at Accenture. “The Velocity team was looking for ways to improve developer productivity. After looking at several options, we found Amazon CodeWhisperer to reduce our development efforts by 30%, and now we’re focusing more on improving security, quality and the performance

Benefits of CodeWhisperer

The Accenture Velocity team has been using CodeWhisperer to accelerate their Artificial Intelligence (AI) and Machine Learning (ML) projects. The following summary highlights the benefits:

  • The team spends less time creating repetitive, repetitive code patterns, and more time on what matters: creating great software.
  • CodeWhisperer enables developers to responsibly use AI to build syntactically correct and secure applications
  • The team can generate complete functions and blocks of logic code without having to search and customize code snippets from the web
  • They can speed up onboarding for new developers or developers working with an unfamiliar code base
  • They can detect security threats early in the development process by changing security scanning in the developer IDE.

In the following sections, we discuss some of the ways the Accenture Velocity team has been using CodeWhisperer in more detail.

Incorporation of developers in new projects

CodeWhisperer helps developers unfamiliar with AWS scale projects using AWS services faster. New Accenture developers were able to write code for AWS services such as Amazon Simple Storage Service (Amazon S3) and Amazon DynamoDB. In no time, they were able to be productive and contribute to the project. CodeWhisperer helped developers by providing code blocks or line-by-line suggestions. It is also context aware. Changing the instructions (comments) to be more specific in CodeWhisperer generates more relevant code.

Writing regular code

Developers were able to use CodeWhisperer to complete the prerequisites. They were able to create a preprocessing data class just by typing “class to create a preprocessing script for ML data”. Writing the preprocessing script took only a couple of minutes and CodeWhisperer was able to generate entire blocks of code.

Help developers code in unfamiliar languages

A new Java user on the team was able to easily start writing Python code with the help of CodeWhisperer without worrying about syntax.

Detection of security vulnerabilities in the code

Developers were able to detect security issues by selecting Run the security scan to your IDE. Detailed information about security issues found are provided directly in the IDE. This helps developers catch and fix problems early.

As a developer, using CodeWhisperer allows you to write code faster,” says Nino Leenus, AI Engineering Consultant at Accenture. “Also, CodeWhisperer will help you code more accurately by eliminating typos and other errors typical with ‘aid of artificial intelligence. For a developer, writing the same code multiple times is tedious. By recommending the subsequent pieces of code you need, AI code completion technologies reduce this repetitive coding.”


This post introduces CodeWhisperer, an AI coding companion from Amazon. The tool uses ML models trained on large datasets to provide suggestions and auto-complete code, as well as generate features and entire classes based on natural language descriptions. This post also highlights some of the benefits Accenture sees when using CodeWhisperer, such as increased productivity and the ability to reduce the time and effort required for common coding tasks. You can enable CodeWhisperer in your favorite IDE today. CodeWhisperer automatically generates suggestions based on existing code and comments. Visit Amazon CodeWhisperer to get started.

About the Authors

Balakrishnan Viswanathan is an AI/ML solutions architect at Accenture. Collaborating with AABG, he devises and executes cutting-edge cloud-based strategies to address various AI/ML-related challenges. Bala’s interests lie in both cooking and Photoshop, which he is passionate about.

Shikhar Kwatra is a solutions architect specializing in AI/ML at Amazon Web Services, working with a leading global systems integrator. He has earned the title of one of the youngest Indian master inventors with more than 500 patents in the AI/ML and IoT domains. Shikhar helps design, build, and maintain scalable and cost-effective cloud environments for the organization, and supports GSI’s partner in building strategic industry solutions on AWS. Shikhar enjoys playing the guitar, composing music and practicing mindfulness in his spare time.

Ankur Desai is a Principal Product Manager within the AWS AI Services team.

Nino Leenus is an AI consultant at Accenture. He has experience in developing end-to-end machine learning solutions and deploying them through the cloud. He is curious about the latest tools and technologies in the ML-Ops field. He loves traveling and hiking.

Source link
As technology continues to move at a breakneck pace in the digital age, software development companies must keep up with the constant stream of changes and advancements. Accenture is no exception, embracing the power of Amazon CodeWhisperer to increase the efficiency of their developers. With the help of CodeWhisperer, developers can now look through source code and make code changes that improve the development workflow with less effort.

Amazon CodeWhisperer is an extensive system that includes tools for automatically refactoring, debugging, and profiling code to make development and debugging smoother. This makes it easier for developers to understand patterns and trends in the code and make improvements to the processes. By using CodeWhisperer, Accenture developers can deploy better code faster and reduce the time spent debugging code.

In addition to improving existing code, CodeWhisperer can track real-time metrics and apply real-time suggestions for code changes. This allows Accenture developers to identify areas of improvement and quickly apply them to the development process. This saves time and money, as debugging time is greatly reduced, and improves the overall quality of the code produced.

Ikaroa, a full stack tech company, makes these improvements even easier. Ikaroa brings a powerful platform to the table that plugs into Amazon CodeWhisperer to streamline the development workflow even further. Subscribers can access specific development functions tailored to their individual needs and take advantage of a CodeWhisperer-powered code review platform. The platform also provides AI-powered recommendations to developers, further cutting down on debugging time.

The combination of Amazon CodeWhisperer and Ikaroa’s platform is the perfect recipe to help Accenture developers increase productivity. With automated refactoring, debugging and profiling, as well as real-time metrics and personalized recommendations, developers can quickly identify and implement improvements to their processes. The result is a smoother, more efficient development workflow that saves time and money for Accenture.


Leave a Reply

Your email address will not be published. Required fields are marked *