{"type":"video","version":"1.0","html":"<iframe src=\"https://www.loom.com/embed/01b88d25b9e74a85b9d0948276ea02de\" frameborder=\"0\" width=\"1670\" height=\"1252\" webkitallowfullscreen mozallowfullscreen allowfullscreen></iframe>","height":1252,"width":1670,"provider_name":"Loom","provider_url":"https://www.loom.com","thumbnail_height":1252,"thumbnail_width":1670,"thumbnail_url":"https://cdn.loom.com/sessions/thumbnails/01b88d25b9e74a85b9d0948276ea02de-bb172ef5a642e36f.gif","duration":675.5301,"title":"Building an Intelligent Agent System for Customer Support | Spencer Reith PartSelect","description":"In this video, I share my project for the PartSelect agent process, focusing on the algorithm that connects various agents to gather information and formulate responses in a chat interface. I explain how agents utilize web scraping as a tool to independently think and communicate, ensuring they gather necessary information before responding to user queries about appliance issues. I walk through the interaction flow, demonstrating how agents ask probing questions and execute tool calls based on user input. Additionally, I dive into the codebase, highlighting the structure of the agents and the web scraping toolkit. I appreciate your consideration and look forward to any feedback or questions you may have."}