In this writing, I want to share how I started to learn using the Power BI Modeling MCP server  together with Power BI Projects (.pbip) and VSCode , and how that experiment turned into a full workflow: building a Contoso  star schema with an AI agent, generating a measure table , cleaning up metadata  (Sort by column), and automatically hiding visual-level filters  in the filter pane by editing the report JSON. This is all from an actual hands-on session; the screenshots I’ll

I didn’t expect the Power BI Modeling MCP Server to reshape my modeling habits. My plan was simple: read the November 2025 Feature Summary, test the feature for a few minutes, and move on. Instead, those “few minutes” turned into a fully immersive exploration where Copilot started behaving less like a text generator and more like a modeling agent. This post is a narrative of that journey — a story told through every screenshot I captured along the way — and how those moments

In this writing, I’d like to share the small experiment I did recently: querying an SVG measure from a semantic model using a Fabric Notebook , scaling it with Python, and displaying it directly in the notebook output. The idea started from a question from my manager: “If the semantic model produces SVG via DAX, can we render it outside Power BI and reuse it somewhere else?” Once I tried it, new use cases started to appear. The Data Model I Used Below is the sample semantic m

In this writing, I’d like to share how I started learning and experimenting with Copilot and AI-driven features  in Power BI and Fabric — and what I discovered about the role of semantic models  in making them work effectively. Prerequisites Before jumping into it, here’s the setup I used for experimenting with Copilot and AI-driven insights in Power BI and Fabric. Power BI Service (Fabric workspace)  — The experiments were all performed in a Fabric-enabled workspace, since C

In this writing, I’d like to share how I started learning about Composite Semantic Models  in Power BI and Fabric — especially now that Direct Lake mode can coexist with Import tables . When this feature first appeared in preview, I was curious how it could help simplify data architecture and improve performance for mixed workloads. After some testing, I’ve learned both the power and the limitations of this hybrid approach. Why This Feature Matters For years, I had to choose

In this writing, I’d like to share how I started to learn and create my own DAX UDF (User Defined Function) library , the pain points I’ve faced while trying to make the functions as general as possible, and how I plan to take the next steps forward. You can explore the project here: jihwankimdata/dax_udf_library How It Started Like many Power BI developers, I’ve written the same logic dozens of times — percentage growth, variance analysis, ranking, or window calculations — s

In this writing, I’d like to share how I’ve been exploring TMDL (Tabular Model Definition Language)  since it was in preview — and why...

In this writing, I’d like to share how I started learning to edit semantic models directly in the Power BI service  and how TMDL (Tabular...

In this writing, I’d like to share how I've learned to dramatically accelerate one of the most common and repetitive tasks in Power BI...

In this writing, I’d like to share what I have learned from a recent Microsoft Fabric announcement that, in my opinion, is one of the...