video1.0<iframe src="https://www.loom.com/embed/4a99528a1875476690551bcd75ec036c" frameborder="0" width="1728" height="1296" webkitallowfullscreen mozallowfullscreen allowfullscreen></iframe>12961728Loomhttps://www.loom.com12961728https://cdn.loom.com/sessions/thumbnails/4a99528a1875476690551bcd75ec036c-a909f61664d7d35d.gif179.8959In this video, I demonstrate how to use Patronus Percival to automatically fix bugs in AI agents. I walk through a simple example where our agent retrieves weather information but initially includes irrelevant details. By using Percival's prompt suggestions, we can optimize the agent to provide only the necessary information. I encourage you to try implementing these prompt fixes in your own projects for better results.