The AI can handle and understand incoming images, but how to handle incoming video? Currently, it replies, "I can only process images at the moment...."

Hi I'm not entirely sure if there's a direct integration for video analysis with the autonomous node. However, one alternative you might want to consider is using Microsoft's Azure Content Understanding, as this tool has the capability to analyze and extract information from multimedia content, including videos. Depending on your use case, you could automate a workflow in which the video is processed by Azure Content Understanding to extract relevant information (such as descriptions, transcripts, object detection, events, or metadata) and then send those results to the autonomous node for further processing or decision-making. Although I can't confirm that there is native integration between the two solutions, in principle it should be possible to connect them using APIs or automation workflows to achieve the functionality you need. https://learn.microsoft.com/en-us/azure/ai-services/content-understanding/overview

It is to handle incoming messages from ads, reels and stories. Sometimes, when the customer replies to the ad, the reels are sent in with the replies. Any idea @loud-crowd-60573 ?