{"type":"video","version":"1.0","html":"<iframe src=\"https://www.loom.com/embed/0ef2dd9e0bdd442cafc7a9fb09a73b0a\" frameborder=\"0\" width=\"1920\" height=\"1440\" webkitallowfullscreen mozallowfullscreen allowfullscreen></iframe>","height":1440,"width":1920,"provider_name":"Loom","provider_url":"https://www.loom.com","thumbnail_height":1440,"thumbnail_width":1920,"thumbnail_url":"https://cdn.loom.com/sessions/thumbnails/0ef2dd9e0bdd442cafc7a9fb09a73b0a-cbf8cb35972f6de4.gif","duration":457.218,"title":"Enhancing Agent Evaluations on the Gradient AI Platform","description":"In this video, I walk you through the agent evaluations experience on the Gradient AI Agented Cloud platform, which I designed. This experience is aimed at helping users understand their agent's behavior and improve its performance through qualitative and quantitative metrics. I demonstrate the evaluation process using the Ariel Silks Lesson Planner agent, highlighting key metrics and the importance of avoiding hallucinations in responses. I also discuss upcoming features, such as enhanced metric explanations and actionable insights for improvement. I encourage you to explore this platform and consider how it can enhance your own agent evaluations."}