From Prompt to Product: Build an AI Agent

Everyone is talking about AI agents. Almost nobody understands how they actually work. We build an AI agent from scratch on stage using HubSpot, pulling back the curtain on every layer: the LLM making decisions, the memory holding context, the tools taking action, and the orchestration tying it together. The audience votes on decisions and debugs the agent in real time. Attendees leave with a clear mental model of how agents work, a replicable process from idea to working agent, and the fixes for the most common failure modes in production.