Nate activates a Copilot power-up that uses ChatGPT to build a system prompt for his AI agent on the Phi model. The catch: if the players miss a deliberately difficult trivia question, a physical robot gets smashed onto the floor. The setup has occasional reliability issues with the n8n automation platform.
And Nate is using his Copilot power-up to get ChatGPT to generate a system prompt for his AI agent. We're using Phi. It's pretty smart. I like it. Although in N8N, sometimes it has some issues. Let's also give it up for our robot friend here. Because this poor little sucker is going to be getting hit to the ground if our players don't have an absolute perfect score. And we may have even designed one question that is going to be very hard for them to get right so that we definitely see some robot smashing. Lockdowns!
