Course Outline
Getting to know AI Builder and Low-Code AI
- Overview of AI Builder features and typical business use cases
- Key aspects of licensing, governance, and tenant setup
- How AI Builder connects with the wider Power Platform (Power Apps, Power Automate, Dataverse)
OCR and Document Processing: Handling Structured and Unstructured Forms
- Distinctions between fixed-format templates and free-form documents
- Preparing training data: tagging fields, ensuring sample variety, and maintaining data quality
- Creating an AI Builder form processing model and assessing extraction precision
- Refining extracted information: validating, normalizing, and managing errors
- Practical exercise: performing OCR on various document types and linking the output to a processing workflow
Predictive Modeling: Classification and Regression
- Defining the problem: qualitative (classification) vs quantitative (regression) objectives
- Preparing features and managing missing data within Power Platform workflows
- Training, testing, and analyzing model performance metrics (accuracy, precision, recall, RMSE)
- Considering model interpretability and fairness in real-world business contexts
- Practical exercise: developing a custom model for churn prediction or numeric forecasting
Integrating with Power Apps and Power Automate
- Incorporating AI Builder models into canvas and model-driven applications
- Designing automated flows to handle extracted data and initiate business processes
- Architectural patterns for building scalable and easy-to-maintain AI-driven solutions
- Practical exercise: a complete scenario involving document upload, OCR, prediction, and workflow automation
Supplementary Process Mining Concepts (Optional)
- How Process Mining uses event logs to uncover, examine, and refine business processes
- Leveraging Process Mining results to enhance model inputs and drive continuous improvement
- Case study: using Process Mining insights alongside AI Builder to minimize manual interventions
Production Readiness, Governance, and Monitoring
- Ensuring data governance, privacy, and compliance when processing sensitive documents with AI Builder
- Managing the model lifecycle: retraining, version control, and ongoing performance tracking
- Implementing models with alerts, dashboards, and human-in-the-loop verification
Recap and Future Directions
Requirements
- Practical experience with Power Apps, Power Automate, or Power Platform administration
- Basic understanding of data concepts, fundamental ML principles, and model evaluation
- Proficiency in working with datasets, Excel/CSV exports, and basic data cleaning
Target Audience
- Power Platform developers and solution architects
- Data analysts and process owners looking to automate operations using AI
- Business automation leaders interested in document processing and prediction scenarios
Testimonials (3)
Practical and hands on labs on report developmemt using Power BI The labs were excellent and the trainer offered very good hands on sessions
Sinzala Sichaanji - Bank of Zambia
Course - Mastering Power Platform: Power Apps, Power Automate, DataVerse, Power BI, and Power Virtual Agents
We did quite complex examples, so we could get a feeling of how the real work with Power Automate Desktop can look like in the real world scenario.
Michal Strnad - MicroNova AG
Course - Microsoft Flow/Power Automate
Dynamic, adaptive, and informative
