<?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/3b418a2b026148b2a7783d754c8c0792&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/3b418a2b026148b2a7783d754c8c0792-573b719f7b5e2e76.gif</thumbnail_url><duration>229.768</duration><title>Mom’s Compass, AI Guided Shopping for Moms 🧭</title><description>Hi everyone, I am Asfiya Saeed, and I presented my Track A AI Engineering project for Mom’s Compass. I built a companion that listens to a mother’s input and classifies it to the right milestone, then pulls verified guidance and exact Mom’s World catalogue products for that moment using a grounded knowledge base. The logic is modular so we can update products or milestones without breaking the code. It includes a safety guardian that stops recommendations and shows a medical deferral if a mother mentions concerns like fever or injury. No action was requested from viewers.</description></oembed>