AWS trains its AI code generator to accelerate app development on MongoDB

Amazon Web Services (AWS) and MongoDB are collaborating for app development and modernisation on the latter’s data platform. As part of the collaboration, artificial intelligence-based code generator Amazon CodeWhisperer will provide enhanced suggestions on MongoDB for developers to follow best practices, ideate quickly, and accelerate application development. 

< id="docs-internal-guid-c110c818-7fff-34a3-b2d2-88996071e7d8">Amazon CodeWhisperer is trained and evaluated on code and libraries specific to MongoDB. To this end, MongoDB and AWS have built 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.

“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,” said Andrew Davidson, senior vice president of Product at MongoDB. 

The optimisations on Amazon CodeWhisperer are available for the five most common programming languages used with MongoDB – C#, Go, Java, JavaScript, and Python. Developers can also take advantage of code Amazon CodeWhisperer features like security scanning and a reference tracker. 

"Amazon CodeWhisperer already provides an optimized 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.” 

To get started, developers need to install the Amazon CodeWhisperer extension for their preferred IDE, provide an AWS Builder ID, and begin using the service for code completion and generation.