I’m building an AI Agent with Evolution API to connect it to WhatsApp. The problem is: I want the AI to stop replying once a human agent jumps into the conversation. From what I can tell, the Webhook input looks basically the same for both AI messages and human agent messages, so I can’t figure out a way to differentiate them (for an IF node maybe). Am I overlooking something in the Webhook payload, or is there another practical way to handle this? Maybe I could design a separate flow with databases to track who’s responding, but that feels overcomplicated, and a non-optimized way to do so. Has anyone dealt with this before? Any ideas or best practices would be super helpful.
This topic was automatically closed 7 days after the last reply. New replies are no longer allowed.