video1.0<iframe src="https://www.loom.com/embed/40e3cd97677f42c8ac5415209afde25d" frameborder="0" width="1920" height="1440" webkitallowfullscreen mozallowfullscreen allowfullscreen></iframe>14401920Loomhttps://www.loom.com14401920https://cdn.loom.com/sessions/thumbnails/40e3cd97677f42c8ac5415209afde25d-fa6a124c9e8fdaf9.gif364.766In this video, I demonstrate how AI category detection using the GPT-40 mini model can be utilized in workflows to identify and close spam conversations. I guide you through setting up AI categories, creating a workflow to categorize and close spam messages, and showcase how the system works with both spam and legit messages. The video emphasizes the importance of detailed category descriptions and showcases the versatility of using AI categories in various aspects of Intercom.