Most AI sessions send you home with notes. This one sends you home with something that runs. You're split into teams, each one led by a hackathon team lead who has actually shipped this stuff before and already has a concept and workflow built. Walk the room and pick which build you want to join: competitive intel, a messaging tester, or a launch tracker that measures impact. No coding background required, bring a laptop, and stretch extensions for anyone who already builds. Powered by a leading AI build platform, to be announced. Sixty minutes building. Then thirty minutes of Q&A with your team lead: where it's likely to fail in production, what they'd do differently, and what to try next back at your desk. Three things you leave with: - A working agent you can point at real data on Monday - A straight answer from someone who has actually shipped this on where it's likely to break - A way to test the next one before you trust it