video1.0<iframe src="https://www.loom.com/embed/fc9c48d9d59e41d2aa3d1ee56675041f" frameborder="0" width="1280" height="960" webkitallowfullscreen mozallowfullscreen allowfullscreen></iframe>9601280Loomhttps://www.loom.com9601280https://cdn.loom.com/sessions/thumbnails/fc9c48d9d59e41d2aa3d1ee56675041f-00001.gif264.533333Hey there! In this video, I'm thrilled to share that we've made grid search work for prompts using Prompt Learner. I'll explain how grid search is traditionally used in machine learning and how we've adapted it for prompt engineering. We'll be working on a multicast classification task with 15 classes, aiming to classify customer messages. I'll walk you through the process of setting up the task, loading the training and test datasets, and creating a prompt. Then, we'll see the performance of our prompt on the test dataset and run a grid search to optimize it. The best part? We achieved a 7% accuracy improvement on the test dataset just by tuning the prompt! Check out the video to learn more and try it out today!