Why You Still Haven't Built Your App


Everyone overcomplicates building with AI.

Especially engineers.

They come from a background where planning is everything.

Think it out 10 times over or problems down the road, right?

I get it, and this used to be my reality.

But it's not anymore, and it's not what I teach today.

Here's the Thing

How engineers use AI and how non-tech people use AI to build things is fundamentally different.

Non-tech people listening to traditional engineers lead to terrible results.

People who just want to build their ideas end up spending time thinking about context-rot, engineering context with repo prompts, writing full specs for apps that...

...will never see the light of day 🥲

This is bullshit if you ask me.

The Real Pattern

I've watched this play out over and over:

Engineers: Weeks planning the perfect architecture

Average builders: Just start with basic prompts

Guess who actually builds apps faster?

My Take

BUILD NOW PLAN LATER.

Your app doesn't need the perfect plan or 17 features.

It needs to solve ONE person's BIG problem well enough that they'll use it.

There is beauty in just building and figuring things out.

What You Should Actually Do

Ignore anyone telling you a plan is the most important thing.

Your only goal right now is to VALIDATE YOUR IDEA.

The smallest viable version of it, not the big grand thing.

Stop watching YouTube videos, stop buying courses, and start building.

Everything else is just expensive procrastination.

Best Tools Right Now

I currently recommend Cursor (or Windsurf if you're on a budget).

But even a tool like v0 by Vercel (a better Lovable) is a solid start.

If you are on ChatGPT Plus, Codex CLI is also an amazing way to start.

​

Talk soon,
Robin

P.S. I share my unfiltered thoughts on AI coding daily on X/Twitter - follow me there for the fastest coverage on everything, as well as my spiciest hot takes on all things AI.

Robin Ebers

Coder of 20+ years teaching non-technical people how to build their own software business in 30 days with AI. No devs or code required.

Read more from Robin Ebers

Hey Reader I need to confess something embarrassing. For years, I was the worst kind of engineer. The kind who spent 100 hours perfecting code for apps that never launched. Clean architecture. Zero bugs. Fully scalable. And completely worthless, because nobody used them. Here's The Painful Truth While I was busy "doing it right"... Non-technical founders were shipping garbage code and making money. My perfect projects were sitting in GitHub repos. Their messy apps took daily payments. The...

Hey Reader, I just spent hours building the exact same app twice. Same prompt. Same tech stack. Same features. The only difference was that one used Claude Sonnet 4.5 (Claude Code), and the other used GPT-5 (Codex CLI). And holy sh*t, the results were not even close. Let me show you what happened. The Test I built a simple to-do list app with user authentication. Nothing crazy. Just login, add tasks, edit them, delete them. I even told both models: "Keep it super secure." Should be easy...

Hey Reader, Two days ago my student messaged me. He was almost angry... "GPT-5 worked for 23 minutes and then said it doesn't understand!" Oof. That's rough, and I know how this feels. But that's when it hit me. We're all prompting AI wrong. Everyone of us. The $200,000 Mistake Big tech pays prompt engineers $200k+/year. Because they know what a difference of good prompts. Imagine telling your GPS "go somewhere nice" instead of an actual address One gets you lost. One gets you there. So I did...