{"type":"video","version":"1.0","html":"<iframe src=\"https://www.loom.com/embed/546bcde3084a4930bcd90e54d0f089dd\" frameborder=\"0\" width=\"3840\" height=\"2880\" webkitallowfullscreen mozallowfullscreen allowfullscreen></iframe>","height":2880,"width":3840,"provider_name":"Loom","provider_url":"https://www.loom.com","thumbnail_height":2880,"thumbnail_width":3840,"thumbnail_url":"https://cdn.loom.com/sessions/thumbnails/546bcde3084a4930bcd90e54d0f089dd-e3784ba4a5b132a2.gif","duration":968.957,"title":"Build an AI Agent With ManyChat Using SiloBox","description":"This Loom shows how to create an AI agent in SiloBox and connect it to a ManyChat account. It walks through creating a workspace, confirming email, obtaining a ManyChat API key, generating an OpenAI API key for a default project, and importing and editing a lead generation prompt that collects name, email, goals, start time, and phone number before sending a booking link. The video then installs a ManyChat template, configures automation rules and custom bot fields using the automation ID, selects the “silo box text response” flow, sets the timezone to Montevideo, and saves and enables the automation. Finally, it demonstrates the setup in an Instagram chat where the agent asks qualification questions, parses the user inputs, and maintains conversation memory."}