{"type":"video","version":"1.0","html":"<iframe src=\"https://www.loom.com/embed/66a186cac15246a984ae140dde9fcc8f\" frameborder=\"0\" width=\"1112\" height=\"834\" webkitallowfullscreen mozallowfullscreen allowfullscreen></iframe>","height":834,"width":1112,"provider_name":"Loom","provider_url":"https://www.loom.com","thumbnail_height":834,"thumbnail_width":1112,"thumbnail_url":"https://cdn.loom.com/sessions/thumbnails/66a186cac15246a984ae140dde9fcc8f-89f827a97809ea47.gif","duration":77.866,"title":"Tracking and Evaluating Agent Performance Platform","description":"This Loom demonstrates the platform for tracking, evaluating, and fixing agents. The speaker runs a test agent and explains how a Python agent-utilized SDK intercepts the call between the agent and supported LLMs, specifically Entropiq and OpenAIR, extending it to a FastAPI backend. The backend evaluates the data, saves results to MongoDB, and renders them in a React frontend, showing runs with traces marked as failed or worked. Finally, it evaluates feedback with evals so users can review outcomes from the run."}