@itsolelehmann: /GOAL GUIDE FOR NON-TECHNICAL PEOPLE /goal is the most time-saving feature in all of AI right now. It's a new command i…

/GOAL GUIDE FOR NON-TECHNICAL PEOPLE /goal is the most time-saving feature in all of AI right now. It's a new command in Codex, Claude Code, and Hermes that keeps the LLM working towards a goal until it's complete. Basically autopilot for complex AI tasks. Here's how it works under the hood: 1. You type /goal and describe the end result you want 2. The AI starts working 3. After every step, it checks itself: "am I done yet?" 4. If no, it keeps going 5. If yes, it stops and tells you Which means you never have to type "keep going" again. When to actually use it: Use /goal for big jobs where you'd otherwise have to go back-and-forth with it a lot. Stuff with a lot of steps and a clear finish line: > "Build my course landing page: hero, 5 modules, 3 testimonials, FAQ, and Stripe checkout" > "Migrate my 80 blog posts from WordPress to Beehiiv, fix every broken image and internal link along the way" > "Process every customer support ticket from last month: categorize them, draft template replies, and document the top 5 recurring issues" Don't bother with /goal for simple tasks like "write me a tweet" or "explain X to me." Regular prompts are fine for those. Save /goal for the long, messy jobs. The reason it's so awesome: You set the destination once and the AI runs the whole job in the background. Fire one off, close your laptop, go for a walk, work on something else, and come back to a finished result. No babysitting or constant back-and-forth, because it doesn't need you in the loop anymore. Here's how to write effective /goal prompts (so you don't waste time/tokens): Paste this into Claude Code, Codex, or Hermes: "Write me a /goal prompt. Ask me what I'm trying to do first, then keep asking follow-up questions until you can describe 'done' in specific, measurable terms." Take what it gives you, type /goal at the front, and run it. Then walk away and come back to a finished job.