video1.0<iframe src="https://www.loom.com/embed/5af335e0c41a4905bd79ebee33da84ef" frameborder="0" width="1720" height="1290" webkitallowfullscreen mozallowfullscreen allowfullscreen></iframe>12901720Loomhttps://www.loom.com12901720https://cdn.loom.com/sessions/thumbnails/5af335e0c41a4905bd79ebee33da84ef-afdb485529f7ed86.gif849.715In this video, I present the results of integrating BrainTrust with Evoli, focusing on how it enhances both our offline and online evaluation workflows. I discuss the logging capabilities that allow us to trace model calls, tool calls, and other relevant data, which can be filtered and reviewed for better insights. I also demonstrate how I used these traces to conduct offline evaluations and monitor online scores, emphasizing the importance of the SQL-like querying feature for dataset management. I encourage everyone to explore the new functionalities and consider how we can leverage them in our ongoing projects. Please feel free to reach out if you have questions or need further clarification on any aspect.