{"type":"video","version":"1.0","html":"<iframe src=\"https://www.loom.com/embed/2fa1195b76324bbeb2dfea1644605d3c\" frameborder=\"0\" width=\"1110\" height=\"832\" webkitallowfullscreen mozallowfullscreen allowfullscreen></iframe>","height":832,"width":1110,"provider_name":"Loom","provider_url":"https://www.loom.com","thumbnail_height":832,"thumbnail_width":1110,"thumbnail_url":"https://cdn.loom.com/sessions/thumbnails/2fa1195b76324bbeb2dfea1644605d3c-00001.gif","duration":335.7,"title":"Vellum Prompt Sandboxes || Overview","description":"In this video, I provide an overview of our prompt sandboxes section. I explain how to navigate the left prompt section on our left side nav and showcase the different prompts available in this workspace. I also demonstrate the comparison mode and chat mode features. The main task at hand is to determine whether a given conversation should be escalated to a human call center agent. I showcase how to compose prompt templates, add chat history, and use variables. Additionally, I highlight the different models available for comparison. No specific action is requested from the viewers."}