Describe AI Builder Flashcards
Define the AI Builder
AI Builder is a Power Platform capability that helps you improve your business performance by automating processes and predicting outcomes. By using AI Builder, you can quickly bring AI to your apps and flows that connect to your business data that is stored in the underlying data platform (Common Data Service) or in various cloud data sources, such as SharePoint, OneDrive, or Azure.
AI models that you create in AI Builder can help provide intelligence to enhance your business. AI Builder simplifies the AI creation experience by giving people with any level of technical skill the ability to add AI capabilities to their apps and flows without writing code. AI Builder also provides prebuilt AI models, where you don’t need to gather data to build and train the model. You can start to use the intelligence right away.
Name 6 things you can do with AI Builder
You can use AI Builder to create custom AI models that suit the needs of your business, or you can choose from a selection of prebuilt models. You can then use the AI from these models in your apps and workflows.
For example, with AI Builder you can:
- Analyze text for classification, key phrases, language, and sentiment.
- Predict whether something will happen.
- Process business card information.
- Process text from images.
- Read and save information from standard documents.
- Recognize and count items in images.
Give 2 examples of how you can use AI in your business
Invoice processing - Companies often receive invoices in large quantities and from a variety of sources, such as mail, fax, email, or in person. Processing these documents and manually entering them into your database can take considerable time. By using AI to extract the text, key/value pairs, and tables from your documents, you can create workflows to automatically pipe the information into your database. You can even create an app to review the information.
Text analysis - Businesses today are collecting more data than ever before. Whether it’s from survey responses, product reviews, user feedback, or support emails, generating the proper insights is important to understanding your business and your customers. By using AI to analyze text, you can identify customer feedback that contains negative sentiment or certain key phrases. Use AI to identify problems and then trigger the necessary workflows to take action.
AI Builder comes with 5 models you can refine/customize for your business needs. Name the 5 models.
- Category Classification/Text Classification (preview): Categorize text by its meaning so it’s easier to analyze
- Entity Extraction (preview): Recognize specific information about your business from data.
- Form processing: Read and save information from standard documents
- Object Detection: Recognize and count things in images
- Prediction: Predict whether something will happen
AI Builder comes with 7 pre-built models which gets you straight to productivity. Name the 7 models.
- Business Card Reader: Automatically process business card information
- Category Classification (preview): Categorize text by its meaning so it’s easier to analyze
- Entity Extraction (preview): Extract entities and their types from text
- Key Phrase Extraction: Extract the key talking points from text
- Language Detection: Identify the language being used in text
- Sentiment Analysis: Analyze positive/negative sentiment in text
- Text Recognition: Automatically process text from images
After you have trained and published an AI model, there are three ways to use your model. Name the three ways.
- As a component in an app (PowerApps)
- As an action in a flow (Power Automate)
- As new data in your database (Power BI)
Which of the following statements is true?
AI Builder is only available in Power Apps.
AI Builder is only available in Power Automate.
AI Builder is available in both Power Apps and Power Automate.
AI Builder is available in both Power Apps and Power Automate.
You have customized a model by using the guided experience. What is the final step that you must take before you can use it?
Publish it
What do you need to do before you can use a prebuilt model?
Nothing. With prebuilt models the data has been gathered, the model has been trained and the model is published.