Connecting Azure Custom Vision with Microsoft Flow

This post covers how to connect Azure Custom Vision Service (over at ) with Microsoft Flow, enabling the use of the prediction within Canvas and Model-driven Apps, the Common Data Service and PowerBI. I’m a huge user and fan of Azure Cognitive Services (there are many) and Microsoft Flow, so being able to use Flow as the platform that connects an App to these services can offer tremendous value. Check out how to do this right now!

Create a Customer Sentiment Solution in Dynamics 365 CE using Azure Cognitive Services

Having a business system that gives actionable insights is important, allowing staff to be able to take information and turn it into useful knowledge relevant to their goals and mission within the business. This mission often involves interacting with customers. In an era of self-service, it’s not all the time the interactions are outbound, and customer interactions can come through via portals, landing pages, surveys and completing feedback forms in any length of time that is not guaranteed. The interactions can result in a, broadly categorised, positive, negative or indifferent experience for the customer. Given not everything is always going so positively with customers, wouldn’t it be amazing to know the general sentiment a customer has from the currently related interactions? This way, users can be alerted if a customer’s average sentiment changes to negative, or before you contact a customer you know if a recent interaction has made them less than impressed, giving you the opportunity to change their impression for the better.

How to set up standard Cognitive Services API Integration in Dynamics 365 (with some custom bits too!)

The release of Dynamics 365 at the end of last year saw some new features available for public preview. One of the features in preview is the Cognitive Services integration, currently available in the US. The Cognitive Services APIs are a group of APIs that span across different categories such as vision or text analytics. A large number of them have a Machine Learning component where a model will be created and then adjusted over time based on the data that it feeds upon, however not all of them require this and instead perform computation without having the ‘learning’ ability.