AI Builder

One of the fundamental challenges with artificial intelligence is that it has historically been out of reach for the many. With limited access to highly sought after resources, drawn out development times, compounded with the added complexity of needing special purpose infrastructure to facilitate the AI development process, there has understandably been various barriers of entry for the broader user base to harness the types of capabilities that fall under the AI domain.

AI Builder is part of Microsoft’s ongoing efforts to democratize AI, empowering users of all skill levels to build, train, and publish AI models in a no-code, guided, point and click environment. Available now in public preview, anyone can infuse AI within their business applications with PowerApps, or add intelligence to automated work processes with Flow.


High-Level Process Flow

  1. Select a model type
    Supported scenarios currently include Binary Classification, Form Processing, Object Detection, and Text Classification.

  2. Connect the model to data
    AI Builder can train models based off data that resides within the Common Data Service.

  3. Configure the model
    Follow the point and click model building wizard interface. No coding required.

  4. Train the model
    This is an automated process handled by the AI Builder service, based on the previously provided inputs.

  5. Publish and use the model
    As an example, there are special AI Builder components available within PowerApps such as a Form Processor or Object Detector. These objects can be connected to a published model.


Supported Scenarios


Binary Classification
An AI model that classifies elements of a given data set into two distinct groups by understanding historical data patterns with historical outcomes. Use this AI model for any business questions that can be answered in one of two options (e.g. yes/no, pass/fail, go/no-go). Use cases: Fraud/Not Fraud, Credit Approved/Credit Declined, Customer Churn/Not Churn, etc.


Text Classification
The process of automatically tagging text entries by learning from previously labeled text items. This enables us to classify unstructured text data stored in the Common Data Service with meaningful business categories. Use cases: Call analytics, feedback processing, content categorization, etc.


Object Detection
This model is able to detect instances of objects that appear within digital images. In order for the model to learn, you must collate a sample of images which contain the objects we are trying to detect. Use cases: Quality Control, Inventory Management, Automation, etc.


Form Processing
An AI model that uses machine learning to extract key-value pairs and table data from form documents. After the model has been trained, you can elect which specific pieces of information need to be retrieved. Use cases: Registration Forms, Work Orders, Invoices, etc.

Lab - Form Processing

Learn how to build, train, and publish a Form Processing AI model that can extract key-value pairs and table data within a canvas app by following this lab hosted on GitHub.


What’s Coming?

  • General Availability October 2019

  • Extend AI Builder to Dynamics 365 and grow up to Pro AI

  • Support for additional AI scenarios

Additional Resources


AI Builder is now available [Duration: 03 mins 27 secs; Posted: 2019-06-10]

Microsoft Business Applications Summit 2019 (June 10-11, Atlanta - Georgia)
Introducing AI Builder [Duration: 53 mins 26 secs; Posted: 2019-06-11]
Learn how to add AI to the Power Platform to solve business problems [Duration: 45 mins 34 secs; Posted: 2019-06-12]

Microsoft Inspire 2019 (July 14-18, Las Vegas - Nevada)
Empowering Citizen Developers with AI Builder [Duration: 05 mins 41 secs; Posted: 2019-07-18]
AI Builder: Adding Intelligence to the Power Platform [Duration: 20 mins 12 secs; Posted: 2019-07-18]