Course Outline
Introduction to AI Builder and Low-Code AI
- Overview of AI Builder capabilities and typical use cases
- Licensing, governance, and tenant-level considerations
- Summary of Power Platform integrations (Power Apps, Power Automate, Dataverse)
OCR and Form Processing: Structured and Unstructured Documents
- Distinctions between structured templates and free-form documents
- Preparing training data: field labelling, sample diversity, and quality standards
- Creating an AI Builder form processing model and assessing extraction accuracy
- Post-processing extracted data: validation, normalisation, and error management
- Practical lab: OCR extraction from mixed form types and integration into a processing workflow
Prediction Models: Classification and Regression
- Problem definition: qualitative (classification) versus quantitative (regression) tasks
- Feature preparation and managing missing data within Power Platform workflows
- Training, testing, and interpreting model metrics (accuracy, precision, recall, RMSE)
- Model explainability and fairness considerations in business contexts
- Practical lab: developing a custom prediction model for churn/scoring or numerical forecasting
Integration with Power Apps and Power Automate
- Embedding AI Builder models into canvas and model-driven applications
- Developing automated flows to process extracted data and trigger business actions
- Design patterns for scalable, maintainable AI-driven applications
- Practical lab: end-to-end scenario covering document upload, OCR, prediction, and workflow automation
Complementary Process Mining Concepts (Optional)
- How Process Mining assists in discovering, analysing, and improving processes using event logs
- Leveraging Process Mining outputs to inform model features and automate improvement cycles
- Real-world example: combining Process Mining insights with AI Builder to reduce manual exceptions
Production Considerations, Governance, and Monitoring
- Data governance, privacy, and compliance when utilising AI Builder on sensitive documents
- Model lifecycle management: retraining, version control, and performance monitoring
- Operationalising models with alerts, dashboards, and human-in-the-loop validation
Summary and Next Steps
Requirements
- Practical experience with Power Apps, Power Automate, or Power Platform administration
- Familiarity with data concepts, fundamental machine learning principles, and model evaluation techniques
- Proficiency in working with datasets, Excel/CSV exports, and basic data cleansing
Target Audience
- Power Platform developers and solution architects
- Data analysts and process owners seeking to implement automation through AI
- Business automation leads focused on document processing and prediction use cases
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
