<?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/5ec18ddb8e2a40b1a7b54784799067fc&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/5ec18ddb8e2a40b1a7b54784799067fc-20a090eabc3857eb.gif</thumbnail_url><duration>160.912</duration><title>MUM&apos;s Gear Promise Rescue Copilot Demo 🚀</title><description>Hi MUM&apos;s World team. I built MUM&apos;s Gear Promise Rescue Co-Pilot using Obsidian as a second brain to support RAG, memory storage, and computer issue resolution. It works in Arabic and English and includes demo scenarios like late formula delivery and card refund timing. When I click Analyze case, it shows a summary of issue type and SLA status, urgency, confidence, and the input, then selects the highest priority using policies in the RAG system. The resolution plan includes promise traces and evidence plus a reply draft in both languages. No action was requested from you.</description></oembed>