MongoDB and Amazon Web Services announced the two companies are collaborating to optimise Amazon CodeWhisperer to provide enhanced suggestions for application development and modernisation on MongoDB’s industry-leading developer data platform that millions of developers and tens of thousands of customers rely on every day for business-critical applications. Trained on billions of lines of Amazon and publicly available code, Amazon CodeWhisperer is an AI-powered coding companion from AWS that generates code suggestions based on natural-language comments or existing code in developers’ integrated development environments (IDEs). Working together with AWS, MongoDB provided curated training data for MongoDB use cases and took part in the evaluation of Amazon CodeWhisperer outputs throughout the training process to promote high-quality code suggestions. While Amazon CodeWhisperer already provided support for building applications on MongoDB, developers can now get enhanced suggestions that reflect best practices, allowing developers to ideate more quickly, rapidly prototype new features, and accelerate application development.
“Generative AI has the potential to not only revolutionise how end users interact with modern applications but also how developers build those applications,” said Andrew Davidson, SVP of Product at MongoDB. “Collaborating with AWS to train Amazon CodeWhisperer on MongoDB is a step in that direction, and developers can now build more quickly and focus on higher-value tasks. With built-in security scanning and the ability to provide source and licensing information when suggestions resemble publicly available open-source training data, Amazon CodeWhisperer now provides developers building on MongoDB a unique experience that will get even better over time.”
“More and more developers are realising the potential of generative AI-powered coding companions to transform how work gets done, giving them more time to focus on solving hard problems,” said Deepak Singh, VP of Next Gen Developer Experience at AWS. “Amazon CodeWhisperer already provides an optimised experience when working on common coding tasks and with AWS APIs. By collaborating with MongoDB, we are extending those capabilities to millions of MongoDB developers. We are excited to put Amazon CodeWhisperer in the hands of even more developers to help them tap into the transformative potential of generative AI.”
As organisations today accelerate deployment of cloud-native applications, developers want to find ways to reduce repetitive tasks so they can focus on building new applications and shipping new features. IDC estimates that 750 million cloud-native applications will be built in the next two years, and that number will likely increase as enterprises and startups alike take advantage of generative AI for both building applications and reinventing end-user application experiences. Developers want to integrate generative AI-powered coding assistants into their day-to-day workflow to help them increase their productivity and focus on harder problems. However, these assistants are often trained on publicly available datasets or a company’s own internal data, and some tools developers build with may not have high-quality, publicly available code samples included as part of a coding assistant’s training data. As a result, these coding assistants can provide some support for these tools, but the recommendations may not conform to best practices. While developers have realised the potential benefit for AI-powered coding companions across many tasks, they want these solutions to be further optimised for the tools they use today so they can unlock the full potential of generative AI across their day-to-day work.
Through this new collaboration to train and evaluate Amazon CodeWhisperer on code and libraries specific to MongoDB, developers can get enhanced suggestions for MongoDB to help them more quickly build and modernise their applications. AWS and MongoDB worked together to train Amazon CodeWhisperer on highly curated content and code from MongoDB documentation, detailed use cases, and common tasks with best practices that developers encounter when working with data on MongoDB. As a result, Amazon CodeWhisperer can help developers more quickly write high-quality code when building data aggregations, performing database operations, and accelerating migration of applications to MongoDB for modernisation. These optimisations are available for five of the most common programming languages used to build with MongoDB, including C#, Go, Java, JavaScript, and Python, while also allowing developers to take advantage of core Amazon CodeWhisperer features, including built-in security scanning and a reference tracker that provides information about the origin of a code suggestion when it resembles open-source training data. Amazon CodeWhisperer is free for individual developers with no qualifications or time limits for generating code, so the entire MongoDB community can start taking advantage of Amazon CodeWhisperer’s enhanced suggestions. To get started, developers simply install the Amazon CodeWhisperer extension for their preferred IDE, provide an AWS Builder ID, and begin using the service for code completion and generation. Amazon CodeWhisperer now helps reduce the amount of time developers spend creating code for building data-driven applications on MongoDB and will continue to be trained to improve and refine code suggestions.
Cascadeo is a managed services and professional services company devoted to fostering customer innovation with a philosophy rooted in ethical engineering practices. “With hundreds of customer cloud deployments under management, we use AWS AI services, such as Amazon CodeWhisperer, Amazon SageMaker, and Amazon Bedrock, to help make us better at consistent operations, faster at responding to customer needs, and radically reduce both the cost of engineering and operations for our company and clients,” said Jared Reminer, Chief Technology Officer at Cascadeo. “Our developers choose CodeWhisperer for its optimised experience when working with AWS APIs, boosting their productivity, and improving code quality when building on AWS. Through this collaboration to train and evaluate CodeWhisperer on curated MongoDB data, our developers can now get intelligent recommendations across both AWS and MongoDB Atlas, streamlining how applications get built and giving developers more time to focus on solving hard problems for clients.”
Gravity9 combines highly skilled individuals with deep engineering knowledge together with customer strategy and design expertise to achieve great results for clients in short timescales. “Developers have always wanted to have the best tools available to them to build and ship high-quality applications with speed, and businesses that offer these tools to development teams have a competitive advantage,” said Eric Allen, Partner at gravity9. “With AI-powered coding assistants becoming increasingly adopted, Amazon CodeWhisperer trained on MongoDB has unique advantages. Developers not only get automatic code suggestions, code that may resemble publicly available open-source training data is flagged to help developers avoid compliance issues. But most importantly, developers can now use Amazon CodeWhisperer to build on MongoDB’s leading developer data platform with MongoDB Atlas to ship next-generation applications at greater speed.”
Redapt is an end-to-end technology solutions provider that brings clarity to a dynamic technical environment. “Developers want to focus on building great applications, but there is a lot of undifferentiated heavy lifting throughout the development process that does not bring value to our clients and distracts from meaningful work,” said Rizwan Patel, Field CTO at Redapt. “Amazon CodeWhisperer has been a game changer for us, removing that heavy lifting, improving code quality, and accelerating development velocity. We are thrilled to see MongoDB collaborate with AWS by providing highly curated data to train and evaluate CodeWhisperer, because it will open up new possibilities when building solutions with MongoDB Atlas.”