Power Platform Release Wave 1 2025: Enhanced Document Processing with AI Builder
In this video, UG Expert and Microsoft MVP Kylie Kiser demonstrates a new feature as part of the Power Platform Release Wave 1, leveraging advanced features with the Azure Document Intelligence integration.
Key Takeaways
- Feature overview: The integration of Azure Document Intelligence enhances the ability to analyze complex documents using advanced OCR, natural language, and layout detection. Currently, it’s available in public preview and generally available in April.
- Creating a document processing model: To create a document processing model, navigate to the AI Hub, select AI models, choose the document model for extracting custom information, and enable the new model processing to explore the improvements.
- Test the new model: You can try the new model version in preview, turn it on for fixed template documents, and extract information such as first name, last name, phone number, and email.
- Document collections: You can create document collections with multiple templates to collect the same data. Upload at least five documents, and tag them based on the information you want to capture, such as first name, last name, phone number, and email. This process remains unchanged from previous versions.
- Tagging: Tagging documents is easy, and the new document processing model can handle more complex forms. The model building process remains the same, but the preview version should offer better accuracy.
