This data story is an exploration of a Power BI semantic model accessed through D3.js visuals and AI agents through the Power BI MCP Server. We challenged the traditional way of building the visualization layer with tools not native to Power BI.
Built using Embedsy Studio, this app shows what becomes possible when you compose analytics experiences freely — beyond the constraints of standard Power BI reports. The underlying semantic model uses Direct Lake mode, reading data directly from Delta tables in OneLake without import or scheduled refresh. This means the story always reflects the latest data, with query performance comparable to Import mode and no duplication of data across systems.
See how AI generates DAX code to query a Power BI semantic model, and how that data is then used to build a D3 visualization — all inside Embedsy Studio.
Ask questions about S&P 500 companies in plain English. The AI writes the DAX query, runs it against the semantic model and returns answers.
Treemaps, scatter plots, bubble charts and histograms — all built in D3.js, querying live Power BI data. No Power BI visual required.
Market cap, profitability, valuation and revenue growth told as a story — not just a dashboard. Each chart makes an argument, not just displays numbers.
Embedsy Studio is in preview and activated on request. Book a demo and we will show you what it can do and enable it for your portal.