{"type":"video","version":"1.0","html":"<iframe src=\"https://www.loom.com/embed/b220917535fd44c08e4c8227a4d9172b\" frameborder=\"0\" width=\"1660\" height=\"1245\" webkitallowfullscreen mozallowfullscreen allowfullscreen></iframe>","height":1245,"width":1660,"provider_name":"Loom","provider_url":"https://www.loom.com","thumbnail_height":1245,"thumbnail_width":1660,"thumbnail_url":"https://cdn.loom.com/sessions/thumbnails/b220917535fd44c08e4c8227a4d9172b-c80119f3fc1be1ba.gif","duration":243.759,"title":"AI Agent that speeds up Gurobi models","description":"In this video, I introduced an AI agent we developed that optimizes Gurobi models to improve their solve times. Using a park and bike hub location problem as an example, our agent achieved an impressive 85% improvement in performance. The process is straightforward—just point it to any GitHub repo with a Gurobi model and run a single command. I encourage you to check out the changes made by the agent and provide feedback, as we would love to hear your thoughts. Feel free to ask for the link to the repo to inspect the modifications."}