Deepak Jonnalagadda

Hey, I'm Deepak. Software engineer in India, building web apps by day and after hours I build my own products with AI. I constantly keep writing it all up: what works, what flops, and what I learn trying to build stuff. Follow along.

Nobody talks about how the "5 more minutes" alarm snooze is the most negotiated contract in human history.

Thanks to AI, you can now build a product nobody wants in a weekend instead of 6 months. Progress.

I've built about 15 products without customers. Not because the code was bad, but because I never knew where the users were. Now the first step isn't code. It's a list of real people I can reach, built before v1. Full breakdown in this article 👇 nitter.gq/hey_supermax/status/21…

As engineers, our instinct is to open the editor first. I followed that instinct for ~15 products, and none of them had customers. Now the first step isn't code. It's a list of real people I can reach, built before v1. Full breakdown in this article 👇 nitter.gq/hey_supermax/status/21…

I built about 15 products before I had a single customer for any of them. Now I don't write code until I can find 500 people who might pay. Full breakdown in this article 👇

Find the people who want it before you write a line of code. Shipping is cheap now. Knowing who it's for is still the hard part.

I wrote down exactly how I build web apps with AI when I only get ~3 hrs/day. The biggest unlock wasn't a tool. It was splitting creative work from careful work. Full breakdown in this article 👉 nitter.gq/hey_supermax/status/21… Let me know your thoughts in the comments.

I wrote a breakdown of how I ship web apps with AI in about 3 hrs/day. Template first, design system next and A full day planning milestones. Then AI builds one milestone at a time while I test previews on my phone. Let me know your thoughts in comments

You sat down to work. Forty minutes later you're still "just checking" things. There's a name for that fog, and a few simple ways to beat it.

I wrote a plain-English guide on asking AI properly, with examples. Most people try it once, get a bland answer, and decide the tool isn't that good. Usually it just didn't know what you knew.

Copy this before asking AI to build a feature: "Before writing any code, list the files you plan to change and why. Then wait for me to say go." It stops the "one small change touched half the project" surprise, and the plan takes ten seconds to check.

Small habit that saves a lot of debugging time: before changing anything, make the bug happen on purpose once. If you can't make it happen on demand, you can't really tell whether your fix worked.

There are 5 races after Austin: Mexico, Brazil, Las Vegas, Qatar & Abu Dhabi. That's 125 points still available after this weekend. So Antonelli needs to leave Austin at least 125 points ahead of everyone. Per F1's own permutations, the only way that happens is: Antonelli wins the race and Russell finishes ninth or lower and Hamilton finishes fifth or lower.

I wrote a plain-English guide on what to do when AI wrote most of your app and you can't read the code when it breaks. Four small habits and a pre-ship checklist you can copy.

Austin is one of the few tracks where Turn 1 is a steep uphill climb right after the start. Braking while going uphill into a hairpin with 20 cars side by side is why the order can change before anyone reaches the top.

A side project rarely stalls because the code is bad. It stalls because version one keeps getting bigger. Pick the one thing it has to do, ship that, and let the rest wait until people ask for it.

Read the whole error message before you paste it into AI. Half the time the file name and line number already tell you where to look, and you fix it faster than the AI could reply.

Give your agent a clear "done" check before it starts. If it can't tell when the task is finished, it either stops too early or keeps going and breaks something else. A test that has to pass, a page that has to load, a file that has to exist. Small thing, big difference.

A good test before asking AI to fix a bug: can you explain the bug in two sentences? If you can't, the AI is going to guess. And so are you.

Building an app with AI is the easy part now. Getting it ready for someone to pay for is where most apps get stuck. I wrote down the 5 things almost every vibe-coded app is missing, in plain English.