AI Builder for Power Automate

Published: Aug 11, 2020

AI Builder is providing new capability for power platform that help you to business process improvement by automatic process and predicting outcomes from input data. Microsoft Power Platform is low code platform which includes 4 major products Power BI, Power Apps, Power Automate and Power Virtual Agents. In this blog, our SharePoint Consultants are focusing on AI Builder capability with Power Automate.

Microsoft Power Platform

AI Builder allows us to add intelligence in our business using Power Automate and Power Apps without need of coding knowledge like we can develop PowerBot with PowerApps. AI builder provides different types of models which provides intelligence and we can use these models in Power Automate. AI Builder is providing the capability to create custom model or train the model according to your business needs.

Power Automation is Microsoft service which makes people’s life easier by providing functionality to convert any repetitive and time-consuming task in automated process using workflow. We can create workflows to send email notifications, data collection, alerting, extract the data from various inputs such as email, document etc.

For example, we can use AI Builder to analyze documents like invoices and store data in database or SharePoint list. We can analyze feedback and reviews, and categorize them using tags like negative, positive, or good etc.

Table of Content

  1. AI model types
  2. Let’s demonstrate with AI Builder for Power Automate
  3. Conclusion

AI model types

AI builder is giving you an option to select prebuild AI Models that you can use in Power Automate or in Power APPs  without train and build the model as per suitable for your business need. It’s mainly divided into two parts i.e. Custom AI Models and prebuilt AI Models. We can also create and train our own custom models.

Custom AI Models

  1. Prediction: Prediction model allows to predict the future outcomes in yes/no patterns based on analysis of the past/historical data. For example, which candidates might be eligible for exam?
  2. Form processing: Form process model allows you to analyse and extract key-value pairs from document and images with help of machine learning technologies. You need at least five documents to get started. For example, you can train the model to extract data such as name, title, invoice amount etc. from the input documents.
  3. Object detection: Object detection model allows you to speed up or automate business process. For example, it helps in inventory management and allow leader to manage relation for the on-site customers in retail business.
  4. Category classification: Category Classification model allows you to analyse large volumes text data in form of email, social media, documents etc. to extract and acted on it. With this model, it can identify text entries with different tags. For example, Spam detection, Customer request routing.
  5. Entity extraction: Entity extraction model allows you to recognize the data based on your business needs. It identifies key element and classify in pre-define categories and transform unstructured data into structured data which is readable by machine. For example, if there is “SharePoint Architect” in your data to named entity recognized will be classified as “Designation”.

Prebuild AI Models

    1. Business Card Reader: Business Card Reader model allows you to extract information from business card images. For example, an extract Name, Job Title, address, email from image.
    2. Text Recognition: Text Recognition model allows you to extract words from images and documents into machine readable format. For example, an extract any keyword from document.
    3. Category Classification: Category Classification model allows you to classify entire text into categories with different tags. For example, there are few prebuilt models for customer feedback such as Issues, Compliant, Customer Service, Documentation, Price & Billing and Staff.
    4. Key Phrase Extraction: Key Phrase Extraction allows you to extract key phrases (main points) from text. For example, “The restaurant was good and there were wonderful staff” then it will extract “restaurant” and “wonderful staff”
    5. Language Detection: Language Detection allows you to detect the language of a text document. For example, the sentence ‘I have a car’ it will return “en” instead of “en-US”. If it cannot detect the language, then it returns unknown.
    6. Sentiment Analysis: Sentiment Analysis model allows you to detect positive, negative, natural, and Mixed sentiments in text. For example, “I am happy while working at TatvaSoft Office” it returns label as Positive.

Let’s demonstrate with AI Builder for Power Automate

We can create our custom AI Model based on business needs OR we can select from prebuilt model.

To access AI Builder, there are two areas available under AI Builder in the left side menu as shown in below image.

  • Build: To build new AI models.
  • Models: Resides your models and shared models.

Power Automate

  • To create first AI model, you need to select model based on your business needs. For that Login into the Power Automate and navigate to AI Builder → Build from left navigation.

Enhance your business with AI

  • Every model has introductory section which gives a brief about each model and help you to identify which model is more suitable for your business to create model.
  • Let’s start with ‘Form Processing’ model. It will open below screen.
    Form Processing
  • Enter the name of AI model and click Create button to create new form processing model as shown in below image.
    Form Processing Create
  • It will open screen as shown in below image.
    Add document examples
  • Add Documents – It needs five or more documents with same layout. To add document select add documents option as shown in below image.
    select add documents option
  • By clicking on Add documents option, you can upload documents from local storage of your PC, SharePoint or Azure Blob Storage.
    upload document from local strorage
  • Select documents and click upload documents button as shown in below image.
    Click upload document
  • By clicking on Analyze button, it will save the documents and start analyzing all documents.
    Click on Analyze button
  • Now, click on Next button.
    Add document example next button
  • Select fields from document. We need to select all fields which needs to be extracted from document. To select field, click on the field and confirm its selection as shown in below image.
    Select fields from document


  • After selecting all fields from document, click on Done.

Click on Done

  • Now, click on Next button.
    Click on Next Button
  • Next step is Model Summary, review the selected fields and click Train button.
    Model Summary
  • Click on Go to Details page button.
    Go to details page


  • By clicking on publish button, it will publish the model. You can also test model by clicking Quick test button.

Publish Button

  • Once the model is published then you can use it in power automate.
  • By clicking on Use Model button, you can use model in Power Automate and Power Apps. There are two options to create the Power Automate. i.e. Use Model as shown in below image and other way by creating new solution/select existing solution from Solution link in left navigation.

Use your Model

  • Let’s start with Use Model, when user will click on Use Model button then it will open the panel as per shown in above screen. By clicking on Create New Flow, it will open below screen to use “Common Data Service (current environment)” actions in flow without creating any solution.

Common data service

  • By clicking on continue button, Flow will be created like the below screen. You can select the necessary parameters such as Document Type and Document in predict action.
    select the necessary parameter
  • By clicking on Save button, flow will be saved.
  • Alternate way to create flow with solution, select solutions option from left side menu of Power Automate.
    Select Solution


  • Create new solution by clicking on New solution button as shown in below image or select existing solution.

New Solution

  • Once solution is created, you can navigate into the solution by clicking on solution name and then select Flow from available options inside New menu.
  • Add Trigger “Manually trigger a flow”, and take document and document type as input from user every time flow runs.
    Manually Trigger a Flow
  • Add a ‘Predict – Common Data Service (Current environment)’ action and select our newly created Form Processing Model. Add document type and document value from trigger.
    Manually Trigger a Flow Predict
  • Now save and test the flow using test button.
  • Select document type from drop down and import document. Click on Run Flow button.
    Run Flow
  • Check predict action output to check extracted field values. Now, you can use this extracted field values in other actions for further processing like we can send information in email notification, insert data in SharePoint or any other resource.


AI Builder which allows you to speed up and improve your business process capability based on provided predefine models or create own custom models to analyse, extract data and predict the future outcomes which help to your business. AI builder is boosting to use power platform more efficient and effective way.

Other Blog resources on Power BI, BI Tools
BI Tools – Microsoft Power BI vs. Google Data Studio
Power Virtual Agents – Chatbot
Collaboration of Bot Framework into Microsoft Team
Power BI + Google Analytics = Power Analytics


  • Leave a message...

Related Articles

Power Apps – Portals (Part 3)

Sep 15, 2020

HIPAA Compliance Healthcare Software Development

Sep 9, 2020

Power Apps – Model Driven Apps (Part 2)

Sep 7, 2020