<?xml version="1.0" encoding="UTF-8"?><oembed><type>video</type><version>1.0</version><html>&lt;iframe src=&quot;https://www.loom.com/embed/126127cb8a4942f49cda37c7c9ece9fa&quot; frameborder=&quot;0&quot; width=&quot;1896&quot; height=&quot;1422&quot; webkitallowfullscreen mozallowfullscreen allowfullscreen&gt;&lt;/iframe&gt;</html><height>1422</height><width>1896</width><provider_name>Loom</provider_name><provider_url>https://www.loom.com</provider_url><thumbnail_height>1422</thumbnail_height><thumbnail_width>1896</thumbnail_width><thumbnail_url>https://cdn.loom.com/sessions/thumbnails/126127cb8a4942f49cda37c7c9ece9fa-c9d4256bc0f4b9f6.gif</thumbnail_url><duration>819.218</duration><title>Scaffolding Enterprise Databricks Apps with MCP 🚀</title><description>In this Loom, I walk through how BeastDBx Studio standardizes an enterprise grade Databricks apps project using MCP and agent workflows. I show a three layer architecture with a builder for talking to Delta or Lakebase tables, a services project that exposes the Flask and Swagger endpoints, and a UI project deployed as a Databricks app, all communicating between each other. I also demonstrate scaffolding projects, bundle deployments, and CI setup, then running commands to build, inspect the workspace, and review what is missing like the .env template and git initialization. I requested you to follow the guided next steps and save notes as you go.</description></oembed>