<?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/90d2b0f283a7418e9e29bcbe47540f5f&quot; frameborder=&quot;0&quot; width=&quot;1728&quot; height=&quot;1296&quot; webkitallowfullscreen mozallowfullscreen allowfullscreen&gt;&lt;/iframe&gt;</html><height>1296</height><width>1728</width><provider_name>Loom</provider_name><provider_url>https://www.loom.com</provider_url><thumbnail_height>1296</thumbnail_height><thumbnail_width>1728</thumbnail_width><thumbnail_url>https://cdn.loom.com/sessions/thumbnails/90d2b0f283a7418e9e29bcbe47540f5f-d5f9ded0d95c75f0.gif</thumbnail_url><duration>386.215</duration><title>PawPowPlus Pet Care Planner Demo</title><description>Hi, I am Varnika and this is PawPowPlus, an AI-powered pet care planning assistant I built as my final project. It has two main parts, a task scheduler that sorts tasks by priority, fits them into the owner time windows, detects conflicts, and lets you mark tasks complete, plus a RAG AI advisor that retrieves knowledge before answering. I tested it with a harness running 24 test cases across Retrieval, Intent Detection, Agent Pipeline, and Scheduler, and it passed 24 out of 24. I also demonstrated an emergency guardrail when a dog collapses, advising contact with a vet right away. No action was specifically requested from viewers.</description></oembed>