<?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/0c7f6e404b2b40a8a6191364f765dce6&quot; frameborder=&quot;0&quot; width=&quot;1768&quot; height=&quot;1326&quot; webkitallowfullscreen mozallowfullscreen allowfullscreen&gt;&lt;/iframe&gt;</html><height>1326</height><width>1768</width><provider_name>Loom</provider_name><provider_url>https://www.loom.com</provider_url><thumbnail_height>1326</thumbnail_height><thumbnail_width>1768</thumbnail_width><thumbnail_url>https://cdn.loom.com/sessions/thumbnails/0c7f6e404b2b40a8a6191364f765dce6-aec08d1710d69416.gif</thumbnail_url><duration>186.529773</duration><title>Gorgias MCP Walkthrough 🎥</title><description>This Loom shows how to use AI with Gorgeous to find customer service frustrations and turn them into reports and direct fixes. In under a minute, it identifies subscriptions and returns as the biggest frustration source and flags subscription cancellations as an AI gap, noting tickets often get bounced to a human because the AI cannot cancel subscriptions. It then uses MCP to generate a clean ticket volume report for the last 90 days with metrics and insights, and supports follow up questions in conversation form. Finally, it can take action by auditing existing instructions and creating new agent instructions for shipping-delay complaints, including generating a discount code and setting up apology support actions.</description></oembed>