video1.0<iframe src="https://www.loom.com/embed/e39d4ef94d5d423e8dce49e477e6fd94" frameborder="0" width="1152" height="864" webkitallowfullscreen mozallowfullscreen allowfullscreen></iframe>8641152Loomhttps://www.loom.com8641152https://cdn.loom.com/sessions/thumbnails/e39d4ef94d5d423e8dce49e477e6fd94-ac3893f5c19373ec.gif139.2In this Loom, I walk through how we use Customer Engine Insight to generate product suggestions from customer emails. First, I generated 200 realistic emails using Napurian, an app I launched to help people stop scrolling by charging per minute after they exceed their limit. Then we classify each email to extract theme, emotion, and intent, cluster them into behavioral patterns, and summarize those clusters into product insights, like adding a daily cap and improving fee transparency. Finally, we add a human feedback loop to improve the pipeline over time. No action was requested from viewers.