<?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/385f24560a2a4a74b55425786c9b3ca4&quot; frameborder=&quot;0&quot; width=&quot;1720&quot; height=&quot;1290&quot; webkitallowfullscreen mozallowfullscreen allowfullscreen&gt;&lt;/iframe&gt;</html><height>1290</height><width>1720</width><provider_name>Loom</provider_name><provider_url>https://www.loom.com</provider_url><thumbnail_height>1290</thumbnail_height><thumbnail_width>1720</thumbnail_width><thumbnail_url>https://cdn.loom.com/sessions/thumbnails/385f24560a2a4a74b55425786c9b3ca4-1d4178e1d0a50784.gif</thumbnail_url><duration>75.158</duration><title>Wayfair Supply Tickets Automated with AI</title><description>This Loom explains how Recall, the Wayfair supply ticket agent running on a Cloudflare worker, accelerates responses across thousands of tickets daily. It describes using a decision cache in front of the model so the agent can quickly pull order, supply histories, and policy history, then draft replies in about 8 seconds for the first ticket. Subsequent similar tickets pop instantly because the cache matches features like category and T number, including partial cache hits. The example shows rapid handling for additional tickets, including different SKUs and lighter runs via cached matches.</description></oembed>