{"type":"video","version":"1.0","html":"<iframe src=\"https://www.loom.com/embed/4e514fd89cdc4c5ba869be5b944cdf28\" frameborder=\"0\" width=\"1662\" height=\"1246\" webkitallowfullscreen mozallowfullscreen allowfullscreen></iframe>","height":1246,"width":1662,"provider_name":"Loom","provider_url":"https://www.loom.com","thumbnail_height":1246,"thumbnail_width":1662,"thumbnail_url":"https://cdn.loom.com/sessions/thumbnails/4e514fd89cdc4c5ba869be5b944cdf28-55c5ef8fcc434c91.gif","duration":99.497,"title":"Detect Furniture Damage with AI Demo","description":"This Loom demonstrates how to detect whether furniture is damaged and determine the severity to support refunds or remedies. The speaker explains that if the item is damaged, customers can request a refund, and if there is a misimport, the company can ship a replacement or offer an apology coupon of 10% or 15% for a next purchase. They then run a quick demo showing an image being analyzed using a “subconscious API,” which returns a check based on the model’s output, including token usage. Athens and Emily introduce the approach and note they use the API connected in a skill to avoid running out of context."}