I've built a production app without ever touching a laptop.

by

Six weeks in, and I still haven't touched a desktop. Everything — architecture decisions, debugging, database migrations, the whole thing — happens through a phone screen and an AI agent doing the actual typing.

What's strange is how different the failure modes are from what I expected. I thought the hard part would be not knowing how to code. It wasn't. The hard part was learning to think in prompts instead of logic — how to describe a bug precisely enough that the agent fixes the real problem instead of patching the symptom, three times, in three different wrong places.

I keep wondering if this is a preview of something bigger, or just a novelty that works because I happen to have a lot of patience and a phone that doesn't die. Curious what others here think: for the people who've built with AI agents — has it changed how you think about programming as a skill, or does it just feel like outsourcing typing?

And for anyone who hasn't tried building this way yet — what's stopped you? Time, trust, or just never having a reason to?

(Also: why do programmers prefer dark mode? Because light attracts bugs.)

39 views

Add a comment

Replies

Best

I'm geniuiuly impressed because I've often assumed a laptop was essential. Your experience makes me rethink that.

 Thanks, Alex! Honestly I assumed the same thing going in — figured I'd need a "real" dev setup eventually. Turned out the phone + AI agent combo handled way more than I expected, though I won't pretend it was without its share of "wait, why did that just break" moments along the way. Happy to share more about the workflow if you're curious — always glad to compare notes with someone else building.

I have forgotten every line and syntax of the coding languages. 🤣🤣

 Ha, fair — I never really "had" the syntax to forget, which might be the cheat code here. I couldn't tell you what a semicolon does or doesn't do in JavaScript if you paid me.

What I do have is six weeks of pattern-matching on what makes the agent go sideways, which turns out to be its own kind of fluency — just not one that shows up on a whiteboard interview. 😂

The website has some UI issue, name isnt visible. I think Dark mode has messed up the header.

Checked on Brave and Chrome
Great idea btw.

 Good catch, and thanks for the kind words on the idea.

Ran into almost the exact same thing on Actually Done — my logo blended right into the header background the moment someone had dark mode on, and I never would've caught it since I never test with dark mode toggled. Turns out relying on a single fixed color for a logo/header is a trap; it looks fine in your own light-mode testing and then quietly breaks for a chunk of visitors you never see fail.

Fix that worked for me: explicitly set the header background color instead of letting it inherit/invert, and pick logo colors with contrast checked against both light and dark. Worth testing in both Brave and Chrome with dark mode on before you call it done — good that you already caught it there.

never finished an app without a laptop, so this caught my attention. For me, your story highlights determination over tools.