<?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/31a71f1626264e68827397a05b785aea&quot; frameborder=&quot;0&quot; width=&quot;1670&quot; height=&quot;1252&quot; webkitallowfullscreen mozallowfullscreen allowfullscreen&gt;&lt;/iframe&gt;</html><height>1252</height><width>1670</width><provider_name>Loom</provider_name><provider_url>https://www.loom.com</provider_url><thumbnail_height>1252</thumbnail_height><thumbnail_width>1670</thumbnail_width><thumbnail_url>https://cdn.loom.com/sessions/thumbnails/31a71f1626264e68827397a05b785aea-dca76245b41ccbe2.gif</thumbnail_url><duration>246.657</duration><title>Categorize with AI | New Action</title><description>In this Loom, I share how I classify web chat conversations and text summaries with automation. I send a webhook payload containing the conversation text to the automation, then the AI branches into three categories like resolved, needs human follow up, or requires escalation. Based on the AI intent, the workflow creates actions such as creating notes or tasks, including an escalation task to the assigned person. I run the webhook and review the activity feed to confirm it worked. No action is requested from viewers.</description></oembed>