I'm not an engineer but I wanted to learn how to be in this developing AI world we find ourselves in
I don't have a CS degree. Never shipped a product. Never started a company. One month ago I didn't know what a Next.js route was.
I built Four-Leaf.ai, an AI career prep platform with voice mock interviews, resume tailoring, and negotiation coaching. It's live, it has users, and I launched it on Product Hunt today.
Here's how that happened.
Started in Cursor. I had an idea and Cursor let me move fast without knowing much. It was great for getting something on screen and learning how code actually works by watching it get written. But I hit walls constantly. I didn't know enough to debug what it generated, and the back and forth slowed everything down.
Moved to Claude Code. This is where things changed. Claude Code let me work more like a product manager than an engineer. I could describe what I wanted at a higher level and iterate faster. It handled more complex tasks and I spent less time stuck on things I didn't understand. The terminal-native workflow felt like I had a senior engineer on call 24/7.
Now running a fully agentic setup. I built an OpenClaw instance on a Raspberry Pi that handles engineering, marketing, and SEO work autonomously. I describe what I need (to my new best friend Hank) and it executes. Content gets written (by my second best friend Frank), code gets shipped (by my third best friend Swank), SEO pages get built. I review and approve, but the heavy lifting isn't me.
What I actually learned:
The tools matter less than the loop. Cursor, Claude Code, agentic workflows. They're all just different levels of leverage. The real skill is learning how to describe what you want clearly enough that AI can build it. That's a new kind of literacy and it's more product thinking than engineering.
The biggest misconception about vibe coding is that it's easy. It's not. You still need taste, judgment, and the patience to debug things you barely understand. But the floor has dropped. You don't need four years of CS to ship something real anymore.
If you're a non-technical person sitting on an idea, the barrier has genuinely never been lower. Not zero. But lower.
Happy to answer questions about the stack, the process, or the parts that sucked.

Replies
Fully agree with this. I've been a web developer for 15 years and most of what I learned formally never made it into actual shipped products. What did make it was knowing what you want to build, being able to tell when something is broken, and having the patience to keep going. I strongly believe that none of that requires a CS degree. The LLMs have just made that more obvious than ever!