video1.0<iframe src="https://www.loom.com/embed/2dd159a3a35f470ab67eb6f56e27321f" frameborder="0" width="2094" height="1570" webkitallowfullscreen mozallowfullscreen allowfullscreen></iframe>15702094Loomhttps://www.loom.com15702094https://cdn.loom.com/sessions/thumbnails/2dd159a3a35f470ab67eb6f56e27321f-b6cc0e8094c45200.gif205.612In this video, I walk you through the process of reviewing your evaluations and understanding the performance of your agent across different simulated conversations. I launched 10 conversations and highlighted key metrics such as average latency, with conversation number 8 showing a latency of 4 seconds, which warrants further investigation. I also discuss the importance of defining custom metrics for various customer types and agent instructions. I encourage you to launch different types of conversations in one run to gain deeper insights into your agent's performance. Please take the time to review the transcript and metrics for each conversation to identify any issues that may need your attention.