<?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/9e920497091c45989e9469c628122ef9&quot; frameborder=&quot;0&quot; width=&quot;1920&quot; height=&quot;1440&quot; webkitallowfullscreen mozallowfullscreen allowfullscreen&gt;&lt;/iframe&gt;</html><height>1440</height><width>1920</width><provider_name>Loom</provider_name><provider_url>https://www.loom.com</provider_url><thumbnail_height>1440</thumbnail_height><thumbnail_width>1920</thumbnail_width><thumbnail_url>https://cdn.loom.com/sessions/thumbnails/9e920497091c45989e9469c628122ef9-21a17f9028bf0807.gif</thumbnail_url><duration>1384.635</duration><title>PRD to UI Generator with Multi-Agent AI</title><description>Hi, I am Roushid Beevi KS. , and I walk through my mini project SPEC to UI Agent- PRD to UIGenerator. It converts a PRD into a UI preview and corresponding React code using a multi agent pipeline, built with React, Next.js, and Tailwind, with PDF and DOC parsing and session memory. In one run, Analyst, Builder, and Reviewer analyze the PRD, generate a component tree and UI code, and validate it, then show a live preview. I demo a dashboard example with download code and a requirement history stored locally in the browser. No action was explicitly requested from viewers.</description></oembed>