For decades, spreadsheets have powered the business world. From financial models to risk analysis, Excel's flexibility has made it the go-to tool for countless critical processes. But this has created a problem: valuable data and business logic locked away in files, maintained through manual, siloed workflows that are difficult to scale, govern, or share.

Microsoft Fabric promises to change this—bringing your data into a unified platform where it can be structured, secured, and reused across any tool. But there's a challenge: migrating complex Excel models to Power BI and Fabric is time-consuming, technically demanding, and risky. How do you preserve intricate business logic? How do you maintain control whilst automating the heavy lifting?

Enter the Model Context Protocol (MCP)—the breakthrough that connects AI agents to Power BI and Fabric. These open-standard servers enable AI assistants like Claude to automate your migration: reading Excel structures, generating Power Query transformations, designing and building lakehouses, notebooks, semantic models, DAX measures and visualisations, and validating the entire workflow through natural language conversation. The AI does the grunt work while you maintain oversight at every critical decision point.

This hands-on training day walks through complete Excel-to-Fabric migrations using AI agents powered by MCP servers. You'll learn how to configure MCP servers, use context engineering to guide AI through your specific requirements, automate the migration workflow from Excel analysis through to deployed Fabric solutions, implement validation checkpoints and quality controls, and develop practical patterns for future migrations while preserving business logic.

Full Day Agenda

** Morning Session (09:00 - 12:30) **

Module 1: Understanding the Migration Challenge and MCP Setup (09:00 - 10:30)

- The Excel migration challenge: Why manual migrations are time-consuming, error-prone, and risk losing business logic

-Introduction to Model Context Protocol (MCP): How AI agents connect to Power BI and Fabric

- Architecture overview: MCP servers, Claude AI, and the Fabric ecosystem

- Hands-on Lab: Environment setup: Installing Claude Desktop/VS code and configuring Power BI and Fabric MCP servers; Authenticating and connecting to Fabric workspace; reading existing semantic models

- Hands-on Lab: Excel model analysis preparation: Understanding the sample financial model structure; Documenting business logic and calculation dependencies; Identifying data sources, transformation requirements, and output expectations

-Coffee break (10:30 - 10:45)

- Module 2: Context Engineering and Excel Analysis (10:45 - 12:30)

- Context engineering fundamentals: How to guide AI agents effectively

- Creating context documents: Business requirements, data dictionaries, validation rules

-Hands-on Lab: Using AI agents to analyze Excel models; Natural language commands to examine Excel structure and formulas; Generating documentation of business logic and dependencies; Identifying data transformation patterns and calculation flows; Creating a migration plan with AI assistance

-Hands-on Lab: Data source preparation in Fabric: Creating Fabric workspace and lakehouse structure; Using AI to generate initial bronze layer ingestion logic; Understanding how AI interprets Excel data structures

-Introduction to validation strategies: How to verify AI-generated outputs

Lunch (12:30 - 13:30)

** Afternoon Session (13:30 - 17:00) **

- Module 3: Automated Power Query and Lakehouse Generation (13:30 - 15:00)

- Translating Excel transformations to Power Query M code

Hands-on Lab: AI-assisted Power Query generation: Using natural language to describe transformation requirements; Generating Power Query/notebook code from Excel formula patterns; Creating silver layer transformations with business rule validation; Implementing data quality checks based on Excel validation logic.

- Hands-on Lab: Lakehouse and notebook creation: Using AI to design medallion architecture (bronze/silver/gold); Generating Python notebooks for complex transformations; Creating delta tables with appropriate partitioning strategies; Implementing incremental processing patterns; Validation checkpoint: Comparing outputs against source Excel calculations

Coffee break (15:00 - 15:15)

Module 4: Semantic Model and DAX Measure Creation (15:15 - 16:30)

- Understanding semantic model design requirements

- Hands-on Lab: AI-assisted semantic model development: Using MCP servers to create semantic models programmatically; Generating star schema from lakehouse data structures; Translating Excel formulas to DAX measures through natural language; Creating calculation groups for time intelligence patterns; Building relationships and configuring model properties

-Hands-on Lab: Visualization and report generation: Using AI to guide the creation of Power BI reports based on required outputs; Implementing interactive features beyond Excel capabilities

Module 5: Production Deployment and Advanced Patterns (16:30 - 17:30)

Version control and documentation: Maintaining AI-assisted code
Security considerations: Ensuring migrated solutions meet governance requirements;
Performance optimization: Tuning AI-generated queries and transformations
Advanced patterns for complex scenarios:
Resources and community support
Open Q&A