{"type":"video","version":"1.0","html":"<iframe src=\"https://www.loom.com/embed/c787943c21bf4ae59ee580828b73ccb1\" frameborder=\"0\" width=\"1920\" height=\"1440\" webkitallowfullscreen mozallowfullscreen allowfullscreen></iframe>","height":1440,"width":1920,"provider_name":"Loom","provider_url":"https://www.loom.com","thumbnail_height":1440,"thumbnail_width":1920,"thumbnail_url":"https://cdn.loom.com/sessions/thumbnails/c787943c21bf4ae59ee580828b73ccb1-d7f4afdf3a22fd39.gif","duration":102.634,"title":"Training AI Agents for Business Negotiations 🤖","description":"Hi everyone, in this video, I present our Negotiate Environment, an innovative platform we've developed to train AI agents in negotiating B2B science contracts. We’ve created a synthetic dataset featuring 200 B2B SaaS scenarios, which is available on Hugging Face, and used Hugging Face TRL with LoRa Finance for training. Our model accounts for dynamic market changes and is deployed on Hugging Face spaces using Docker. I also demonstrate how the agent initiates a negotiation and successfully reaches a deal with a vendor. I encourage you to explore the environment and provide feedback on its functionality."}