Today’s live is up above. Thank you to Julia | Taking you global and everyone else who showed up!
If your team is evaluating something a vendor is calling an AI agent, this session gives you a working definition and a 5-part check you can run this week to determine if it’s actually an agent.
I walk through the anatomy of an AI agent (a three-part loop plus two supporting systems), then apply it to two Zapier products to show the difference between an automation being marketed as an agent and something that fits the definition. Roughly 14 minutes.
On Sunday, I’m publishing the paid follow-up: How AI Agents Actually Work Under the Hood. It walks through how to build a multi-agent system, with every one of the five parts labeled inside the build. You’ll see how a sub-agent becomes a tool for the parent agent, how memory carries context across every step, and how the parent decides what to dispatch next based on what came back. You can copy the setup and adapt it to anything your team runs regularly.
See ya soon!
