{"type":"video","version":"1.0","html":"<iframe src=\"https://www.loom.com/embed/94282a1b9a3f4a729b6e87c7bcf85bca\" frameborder=\"0\" width=\"1366\" height=\"1024\" webkitallowfullscreen mozallowfullscreen allowfullscreen></iframe>","height":1024,"width":1366,"provider_name":"Loom","provider_url":"https://www.loom.com","thumbnail_height":1024,"thumbnail_width":1366,"thumbnail_url":"https://cdn.loom.com/sessions/thumbnails/94282a1b9a3f4a729b6e87c7bcf85bca-efb4d1738e04f04d.gif","duration":293.072,"title":"Project: WhatsApp AI Agent Demo with Voice and Image","description":"In this Loom, I show a WhatsApp AI agent that can communicate with users through WhatsApp. It handles text, audio, and image inputs, then uses company input data to generate replies and manages the conversation flow. I test the workflow by sending six messages, and it queues them in Redis, waits about 10 seconds, then hands off to a RouteGroup agent to decide response or general info. I also send a voice message and an image, and it downloads the media, transcribes with an OpenAI model, and replies back via WhatsApp. No action is explicitly requested from viewers."}