3 apps. 1 week. Zero code.


Hey Reader,

Last week I built a mobile app, a Mac desktop app, and a web app.

From scratch.

I still can't believe I'm typing this. But it happened.

And it was WAY easier than any developer will ever admit.

Here's what I built and what I learned.

#1 - MacroPulse (Web App)

I had this old project gathering dust.

A daily financial tracker that gives you one "pulse" every day about what's happening in the markets.

No doom-scrolling. No anxiety. Just the essentials.

But the old version was a mess. So I decided to rebuild it.

Here's the thing nobody talks about:

You can point AI at an old codebase and basically say "learn this, then build me something better."

That's exactly what I did.

I used Codex CLI with GPT-5, gave it my old app as a reference, and went to bed.

When I woke up?

The app was working.

Not perfect. But it didn't just do what I asked. It actually FIXED bugs I'd been ignoring for months.

While I was sleeping.

#2 - Augenblick (Mac Desktop App)

This one was personal.

I grew up building desktop apps with a language called Delphi back in the early 2000s.

But 25 years later, I wanted to see if I could still do it.

So I built an open-source note-taking app with a weird twist:

It automatically deletes notes you don't touch for 7 days.

Why do something like this?

Because I have ADHD and my notes are a disaster.

Tens of thousands of files I'll never look at again.

The result was that this was actually FUN.

Turns out you can use web technologies to build native desktop apps that feel... native.

I used something called Tauri (similar to what Cursor uses, but lighter).

Totally doable. Even if you've never touched "desktop apps" before.

#3 - MacroPulse Mobile (iOS & Android)

This happened a few days ago.

One of my students shipped his own mobile app to the Android store.

And I thought...

"If my students are shipping mobile apps... maybe it's time I do too."

So I pointed the AI at my web app and asked, "What are my options to turn this into a native app?"

After some back-and-forth, it built a fully working mobile app in under an hour.

Took me about 3 more hours to polish the interface.

But the takeaway was that this was just as easy.

IF you know the fundamentals of building with AI.

You can join the TestFlight (iOS only for now) right here - it's free!

The Real Lesson Here

Every day you spend obsessing over new tools, new models, new editors, "the next big thing"...

Is a day you could've shipped something.

Ralph Loops. Clawdbots. Chinese AI models. The latest AI editor.

It's all noise.

You're wasting the opportunity of a lifetime by getting sucked into the hype.

Pick one tool. Go all in. Build something.

That's the whole game.

Talk soon,
Rob

P.S. If you want the exact system I used to build all three apps, that's what my AI Building's Blueprint teaches. Non-technical founders are shipping their first apps in weeks, not months.

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, Two new AI models dropped this week. Everyone on X lost their minds. The hot takes were flying. "Claude Opus 4.6 s dead!""GPT-5.3-Codex is finished!" I ignored all of it. Instead, I spent 5 straight days building real apps with both Opus 4.6 and GPT-5.3 Codex. And I need to be honest with you about what I found. Because the truth is messier than anyone wants to admit. The 4 Biggest Complaints About Claude Opus Before this update, people had four main gripes with Claude's top...

Hey Reader You read the correctly. I built a mobile app in 4 hours. I was inspired by Jan, a student of my AI Builder's Blueprint, who did it two days ago himself. You can check out his app on this website. So last night around 9:30pm, I had one of those "what if" moments. I stared at one of my web apps (macropulse.ai) and thought: What would it take to turn this into a REAL mobile app? Not a wrapper. Not a web view pretending to be an app. But an actual native mobile app. So I did what any...

Hey Reader, I need to get something off my chest. We're living in the era of AI slop. Everyone's obsessed with shipping fast. Nobody gives a shit about building something that actually works. What Has Changed I've been writing code for 20+ years. Led product teams. Ran a UI/UX agency. Built apps before "vibe coding" was a thing. But right now, I'm embarrassed by what I see. Buggy software everywhere. Companies ignoring their users. Zero testing. Zero quality control. Just ship it. Push it...