Date: 27th April 2026
Time: 10am to 4pm
Location: Cathedral View, Carlisle Place, London SW1P 1NL Directions

This event is now full. We will be running a repeat event in May. If you would like advance notice of this (before it appears on meetup), please sign up for our LBAG interest list newletter
This is a full day training on data modelling in Power BI on 27th April 2026. Data Modelling is the core skill needed to build good, correct Power BI reports. We will firstly build a basic semantic model (fact, dimension, and dates tables, based on the star schema pattern). We will then use AI agents via the Power BI Model Context Protocol (MCP) server to directly improve and document our model.
Please bring a full charged laptop with Power BI Desktop installed.
We set up and configure the software and environment that we need to firstly build a semantic model in Power BI, then the extra steps if we want an AI to directly improve it.
We build a star schema data model (dimension, fact, date tables) from scratch either in Power BI Desktop or Power BI online.
We will use sample data with almost perfect data quality so we can focus on modelling and not data cleaning.
We use an AI (either Claude or GitHub Copilot) and the Power BI Model Context Protocol (MCP) Server to directly improve a Power BI semantic model (tables, columns, measures, formats, relationships, hierarchies) with natural language instructions.
So that the course gets off to a flying start, we are running an optional 1-hour virtual session two weeks beforehand on April 13th where we guide people through the setup of Power BI Desktop and a few other things that will be needed for the course. Most attendees will know how to do this already, but we want to make sure that everyone is ready to go on the day of the course.

A draft semantic model. How would you improve it?

TMDL offers a fast route to connect a Dates table

Claude is connected to Power BI via the MCP server and able to review and improve the model

Claude Desktop running the MCP Server