{"type":"video","version":"1.0","html":"<iframe src=\"https://www.loom.com/embed/385f24560a2a4a74b55425786c9b3ca4\" frameborder=\"0\" width=\"1720\" height=\"1290\" webkitallowfullscreen mozallowfullscreen allowfullscreen></iframe>","height":1290,"width":1720,"provider_name":"Loom","provider_url":"https://www.loom.com","thumbnail_height":1290,"thumbnail_width":1720,"thumbnail_url":"https://cdn.loom.com/sessions/thumbnails/385f24560a2a4a74b55425786c9b3ca4-1d4178e1d0a50784.gif","duration":75.158,"title":"Wayfair Supply Tickets Automated with AI","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."}