video1.0<iframe src="https://www.loom.com/embed/fe1be4a7729145a3aedaac131e35806b" frameborder="0" width="1730" height="1297" webkitallowfullscreen mozallowfullscreen allowfullscreen></iframe>12971730Loomhttps://www.loom.com12971730https://cdn.loom.com/sessions/thumbnails/fe1be4a7729145a3aedaac131e35806b-1708719589632.gif347.939In this video, I, one of the founders of Athina, will demonstrate how to use our platform to monitor and evaluate LLM applications. I will show you the monitoring dashboard, where each role represents an inference call to the LLM. You can log inferences from various models and extract metrics like latency, token usage, and cost. You can also tag your data and filter it based on different attributes. I will explain how to view traces and evaluate their performance using different evaluators. No action is requested from viewers.