ML Workflows without Code using Microsoft Flow #ArtificicalIntelligence #MachineLearning #MicrosoftFlow #CognitiveServices @MicrosoftFlow @sbisson

Microsoft Flow templates for social media from flow.microsoft.com

Microsoft Flow allows users to connect applications to improve workflows and increase productivity. These automated workflows are used for simple tasks like collecting twitter messages into an excel file OR sending a text message when you receive an email from your boss.

Turn repetitive tasks into multistep workflows. For example, with a few clicks capture tweets and add them as leads in Dynamics 365, subscribers in Mailchimp, and more…

Recently, Microsoft added several machine learning connectors to Flow for computer vision, text analytics and more! In one example, the computer vision connector was used to create a tool for content moderators. This Flow flags racy images uploaded to SharePoint and sends an email to the content moderator for review.

@sbisson recently covered AI and Microsoft Flow on Infoworld and highlights that these flows can be created without writing any code making it easy for anyone to put together a simple app. With new Flow connectors added regularly and the addition of cognitive services, this lowers the barrier to entry for getting a machine learning workflow up and running.

Tools such as Flow (and the related Logic Apps) are a useful way to implement simple apps that link disparate microservices. There’s no need to think about infrastructure, only the services you’re using as triggers and actions. As an abstraction of common distributed application design patterns, it’s a useful way to work, especially if you’re building an application that won’t get a lot of demand or where it’s hard to justify more development resources.

Adding machine learning to Flow gives you more tools for processing data as it passes through a workflow, either deriving insights or transforming content. Using Azure Cognitive Services this way gives you access to both pretrained and, in the case of Custom Vision, custom models. It’s a combination that should get you working with machine learning apps a lot more quickly than traditional development techniques, developing skills and concepts that can be used across your entire business.

If you would like to see some more examples of Flows in action check out these videos. If you’d like to learn more about cognitive services on Azure take a look here.

October 10, 2019 AT 4:49 pm