Eric Siu explains how to use the /go workflow for AI agents effectively. Vague instructions fail, but specific tasks with clear definitions of done work: design 50 ads, create three landing-page variations. Tools like OpenClaw, Hermes, and Mobbin MCP let agents run richer experiments.
So the way /go works is define what you want and you should define specifically what the definition of done is and it can get that thing done for you. And ideally it's something that's a little clearer, like, hey, I want you to design 50 ads for me in using this initial design over here. And I want you to use this text, or maybe I want you to do 3 landing pages, 3 landing page variations. And I want to, I want you to pull from this Mobbin MCP, which actually has a bunch of designs and screens that you can pull from. The more you connect your agent, like an OpenClaw agent or Hermes, the more you're going to find that you can run more interesting experiments with it.
