video1.0<iframe src="https://www.loom.com/embed/94282a1b9a3f4a729b6e87c7bcf85bca" frameborder="0" width="1366" height="1024" webkitallowfullscreen mozallowfullscreen allowfullscreen></iframe>10241366Loomhttps://www.loom.com10241366https://cdn.loom.com/sessions/thumbnails/94282a1b9a3f4a729b6e87c7bcf85bca-efb4d1738e04f04d.gif293.072In 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.