<?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/c682ec8d7d694bb0b081b477279aec03&quot; frameborder=&quot;0&quot; width=&quot;1280&quot; height=&quot;960&quot; webkitallowfullscreen mozallowfullscreen allowfullscreen&gt;&lt;/iframe&gt;</html><height>960</height><width>1280</width><provider_name>Loom</provider_name><provider_url>https://www.loom.com</provider_url><thumbnail_height>960</thumbnail_height><thumbnail_width>1280</thumbnail_width><thumbnail_url>https://cdn.loom.com/sessions/thumbnails/c682ec8d7d694bb0b081b477279aec03-0fb396676a8ceac4.gif</thumbnail_url><duration>135.76533300000003</duration><title>Facebook Messenger AI Assistant Workflow Overview</title><description>This Loom explains a Facebook Messenger Assistant workflow John built to automatically respond to customer inquiries and capture leads outside business hours. It uses n8n, MetaWebhook, OpenRouter, an AI agent, and a custom knowledge base stored in Google Docs to instantly understand questions, retrieve relevant information, and send answers back through Messenger. The workflow also escalates complex questions when needed and includes a Meta/Facebook verification step at the top of the setup. John demonstrates that sending a message triggers the verification, fetches knowledge-base information, and returns the response successfully.</description></oembed>