Course Outline
Introduction to AI Builder and Low-Code AI
- Capabilities of AI Builder and applicable operational scenarios
- Licensing frameworks, governance structures, and tenant-level management
- Overview of Power Platform integrations, including Power Apps, Power Automate, and Dataverse
OCR and Form Processing: Handling Structured and Unstructured Documents
- Distinctions between structured templates and free-form document formats
- Preparation of training data: field labeling, sample diversity, and quality standards
- Development of AI Builder form processing models and assessment of extraction precision
- Post-processing of extracted data: validation protocols, normalization techniques, and error management
- Practical exercise: OCR extraction from varied form types and integration into processing workflows
Prediction Models: Classification and Regression Analysis
- Problem definition: distinguishing between qualitative (classification) and quantitative (regression) objectives
- Feature engineering and management of incomplete data within Power Platform workflows
- Model training, validation, and interpretation of performance indicators (accuracy, precision, recall, RMSE)
- Model interpretability and fairness assessments in professional and government applications
- Practical exercise: creation of a custom prediction model for churn scoring or numerical forecasting
Integration with Power Apps and Power Automate
- Incorporating AI Builder models into canvas and model-driven applications
- Establishing automated workflows to process extracted data and initiate operational actions
- Architectural patterns for scalable and maintainable AI-driven solutions for government use
- Practical exercise: comprehensive scenario involving document upload, OCR processing, prediction, and workflow automation
Complementary Process Mining Concepts (Optional)
- Application of Process Mining to identify, analyze, and optimize processes using event logs
- Utilization of Process Mining outputs to inform model features and automate improvement cycles
- Practical example: leveraging Process Mining insights alongside AI Builder to minimize manual exceptions
Production Deployment, Governance, and Monitoring
- Data governance, privacy safeguards, and compliance requirements when processing sensitive documents with AI Builder
- Model lifecycle management: retraining schedules, version control, and performance monitoring
- Operational implementation through alerts, dashboards, and human-in-the-loop verification
Conclusion and Recommended Next Steps
Requirements
- Proficiency with Power Apps, Power Automate, or Power Platform administration
- Familiarity with data concepts, foundational machine learning principles, and model evaluation methods
- Experience working with datasets, Excel/CSV exports, and basic data cleansing techniques
Target Audience
- Power Platform developers and solution architects
- Data analysts and process owners seeking AI-driven automation solutions
- Business automation leaders focused on document processing and predictive 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