<?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/9de7ae8fd2fb47da837e2a27da6983be&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/9de7ae8fd2fb47da837e2a27da6983be-cc537db13459d193.jpg</thumbnail_url><duration>482.515</duration><title>Automated Lead Management Pipeline</title><description>This Loom explained that an AI workflow automatically handles submissions from the website inquiry form, from capturing them to saving them in the CRM. It consists of five main stages: a webhook listener, an inquiry validator (determining if it&apos;s serious or a troll), priority scoring, an AI agent that creates a personalized draft reply acknowledging the inquiry and suggesting a solution, and encoding and data filing in the CRM. The author uses Google Sheets with three sheets: input (valid inquiries), invalid inquiries, and processed inquiries as a backup in case of an outage. The demo showed a troll spam message and a serious inquiry with business intent, and it was shown that new rows appear, along with priority, process status, and that the draft reply is ready to be reviewed and sent.</description></oembed>