<?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/fbef8efeb0074ca09bac96eb983dd4ac&quot; frameborder=&quot;0&quot; width=&quot;1664&quot; height=&quot;1248&quot; webkitallowfullscreen mozallowfullscreen allowfullscreen&gt;&lt;/iframe&gt;</html><height>1248</height><width>1664</width><provider_name>Loom</provider_name><provider_url>https://www.loom.com</provider_url><thumbnail_height>1248</thumbnail_height><thumbnail_width>1664</thumbnail_width><thumbnail_url>https://cdn.loom.com/sessions/thumbnails/fbef8efeb0074ca09bac96eb983dd4ac-373ce4d9b5bb9023.gif</thumbnail_url><duration>211.303</duration><title>Multi-agent Web UI demo - Kiroween [video3]</title><description>In this video, I demonstrate a UI I built for my submission to the KiloWin 2025 challenge, showcasing its capabilities through a Python web demo. I have created 72 unit tests and eight evaluation scenarios to ensure the solution&apos;s reliability. During the demo, the AI agent classified a taxi service application as limited risk, with a confidence level of 90 and a risk score of 45, providing key recommendations for improvement. I encourage viewers to review the testing framework and evaluation outputs, as they are crucial for understanding the solution&apos;s effectiveness. Your feedback and insights would be greatly appreciated to enhance my submission.</description></oembed>