How should I learn AI right now? Should I learn AI workflow tools like Hermes, Claude, Codex, or go the old way like NAN or make or mix them both?
My recommendation is to start with one of my NAND courses to get up to speed on visual processes and how automation works in those flows. Immediately after, take a big cloud‑code course to learn how to apply Claude to that foundation. It's important to understand basics like JSON and how data moves through nodes on a graph; once you have that, Claude code becomes capable of handling a lot for you.
First, I’d join a community like Maker School—not just to use my own products but because membership gives you deep discounts (often a 10x return) on AI platform credits and payment‑processing fees. With those savings I’d start by learning a visual drag‑and‑drop automation builder (such as the n platform) for about four to six hours; that teaches you the fundamentals of systems, workflows, JSON, HTTP requests, etc., which accelerates everything else. Next I’d spend another four hours on a Claude‑code course that covers the technical setup, agent communication, model selection, and so on—roughly ten hours total. After that foundation, I’d devote virtually all remaining time to acquiring customers; the first 90 days would be less than 1% spent on learning and the rest on outreach. You need a customer to actually enter the arena, so I’d use Maker School’s day‑by‑day accountability to hit call and outreach targets, then loop back to upsell from any lower tier to higher ones as the relationship grows.
Yes, I still recommend learning tools like Make and N8N. The simplest way to get work as a total newbie is to sign up on platforms like Upwork and apply for jobs that require those tools. Learning N8N instantly opens a massive pool of jobs—there are dozens posted every hour. The same goes for Make.com, and even Claude Code has a market. Once you know the basics, you can pitch N8N, Make, or any other automation in your proposals. It doesn’t take long to become fluent; a 4‑to‑6‑hour course can get you up to speed. Think of it like unlocking new areas in a video game—the fog of war lifts after you spend a few hours studying the visual workflow. These tools are visual, so your brain can grasp them faster than raw code, and they also train you to think in systems, which later helps you prompt AI models like Claude. You don’t need a CS degree—just a few focused hours and you’ll have a marketable skill that feeds directly into AI agency work.
Sure. Just go to my Gumroad and download the 110-step roadmap to $25k a month with automation. It walks you through everything you need to know to get up and running with a basic AI automation agency—defining your niche, picking a business name, building five case studies, buying your main and tertiary domains, and so on. I usually have about 10 people going through it with me. Trust the man with the expensive light pole; check it out and let me know if you have any questions.
You don’t need to become a mathematician or rebuild a GPT from scratch. The deep‑under‑the‑hood details are only about 2 % of the value. Focus on prompt engineering – it’s an extraordinarily high‑income skill – and combine it with no‑code tools. Spend time interacting with the models as much as possible, and you’ll quickly move into the top 10 % of AI consultants. Regarding the school program, everything I teach is already available for free on my YouTube channel. The program charges only for the implementation support and accountability that help you actually apply the knowledge and get results.
ai automationprompt engineeringlearning resourcesschool program