The Box Skills Kit enables users to build custom "Box Skills" that apply the AI technology of their choice - such as image recognition, speech-to-text transcription, natural language understanding, and more - to content in Box. Box Skills, says the company, are a new type of application that automatically enhance content as it's uploaded to Box.
Box Skills process files using third-party machine learning services - such as IBM Watson, Microsoft Azure, Google Cloud Platform, and Amazon Web Services - and write the results as metadata on the file object in Box using the company's existing APIs. This new framework, says the company, leverages a highly-scalable and reliable event pump to trigger user functions based on activity in Box.
"A Box Skill could, for example, analyze images using a computer vision algorithm to detect objects or extract text from those images and tag them in Box with metadata," says the company. "The metadata applied by Box Skills improves the user experience in Box, informs our search capabilities, and can even trigger advanced functionality like automations and policies."
An automated demo is available that creates and deploys a sample Box Skill that accepts a file and prints sample metadata to the file. Once successfully deployed, users can modify the demo code and integrate the AI technology of their choice.
Tutorials and sample code for building custom Box Skills are available in the developer documentation Introducing Box Skills . An upcoming webinar in January will offer a hands-on virtual workshop with the Box Skills Kit.