AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
How Do You Handle That Feedback?
Aminit has built an option for the agents to correct where they noted that the ai had flagged the intent incorrectly. So every time tey see that, they'll just frum the drop ton manou select the correct intent. Once we collect enough data, awe can just feed that back into the model and up date it without having to manually label you know, hundreds of thousands of questions every every now and then.