What was the very first project you vibecoded with AI?

On Product Hunt, I can see many people launching their products using "vibe-coding tools" like , , or

I reckon many people who created something with them are usually developers who didn't have enough time for building a side idea before, but with AI, they could make it happen.

I am not very technical (know some coding/programming basics), but without the help of a tutorial or ChatGPT, I would hardly build a whole project.

Question not only for developers (but also tech newbies):

What was THE FIRST THING YOU VIBECODED?

  • Feel free to share the link or the picture

  • What tool did you use?

  • What was the most difficult part?

  • Did you earn any money with that?

Here is mine:
– It was supposed to be a directory of Bluesky tools

– I used by

– The most difficult parts were to define something + It also rewrote good parts of the code, so it was kind of a mess for me.

– I haven't earned any money because I haven't published the project. (I abandoned it. :D)

4.3K views

Add a comment

Replies

Best

I just launched my first one today

Cogni is a Chrome extension for people who've noticed their own ideas being plagued by generic AI outputs.

I saw it in my own chat logs. One evening I read back through my recent ChatGPT prompts and realised how many started with "give me ideas for" or "write me a" on things I hadn't tried to do myself first. I'd skipped straight to twenty AI options without ever generating one of my own to measure them against. I wasn't choosing. I was just picking from a menu it wrote.

So Cogni puts that part back. It watches your ChatGPT or Claude prompts and, on the ones where you're handing over the creative or strategic work, asks for your inputs, including one or two of your own ideas before the AI answers. The whole thing is grounded in a stack of research, over ten papers now, including scientists at Harvard, MIT, UPenn and Microsoft, on how unstructured AI use erodes independent thought. Everything happens in your browser. Your prompts are never sent anywhere or saved.

thats what I did:

Videplayer with Interpolation and a few gimmicks. just a free player, not like others who deactivate some feature after being a month offline or something. I simply wanted to share the joy I have with others.

My 1st vibe code project is which generate transcript just by entering Youtube video URL.

I'm using next.js, no backend was required for this project. Deployed on hostinger shared hosting.

Use my tool and share your feedback.

If you need any help for such kind of projects, I'm here to help you.

Budget management like so many people :)

The first thing I vibe coded was Concierge for Role Model AI. It started as an experiment to see how far AI assisted development could go and quickly turned into one of our core products.

After that, I built Inner Voice, and then SELF OS.

The hardest part wasn't writing code. It was learning how to communicate with the AI effectively. Better prompts, breaking features into smaller milestones, and constantly reviewing the output made a huge difference.

Vibe coding has completely changed how I build. What used to take weeks can now be prototyped in days, which lets me spend more time refining the product instead of fighting the initial implementation.

The first thing I vibecoded was the firmware for v1 of the Sankhya field node.

It ran on an ESP32 and communicated with RS485/Modbus soil sensors to collect moisture, temperature, pH and EC readings, connect to Wi-Fi, and upload the data to a cloud dashboard.

I used ChatGPT extensively to help structure, debug and iterate on the firmware.

The hardest part was not writing individual functions—it was making the complete field cycle reliable: powering sensors, reading different Modbus devices, handling connectivity failures, conserving battery, and ensuring the node recovered safely after something went wrong.

It did not earn money directly, but it became the foundation of Sankhya Farms, which is now a working free and open-source agricultural IoT platform deployed in my orchard.

Replit felt like magic — right up until my project was done, $1,000+ deep, and I found out there was no easy way to build it for mobile.

Then the second wall: getting my own project off the platform was ridiculously hard.

Switched to Claude. Steeper learning curve, but I could actually ship a mobile app. Bought a Mac for it too — one machine, both platforms, way better dev experience.

My first vibecoded project was BuildReact AI — I just typed out what I wanted, and within minutes had something working. That "wait, it actually built this?" moment is what pushed me to build Dropler.AI — so anyone could have that same experience for React Native apps specifically.

In my case, i built . This came out of seeing a lot of ads on card gaming sites. vibe coding does lead you into a rabbit hole. I feel its important to define what you want. With AI....it could lead you to a slippery slope

For me, my first successful launch was with , an all-in-one workspace that lets you manage work better. I initially built it for remote workers who can't organize their work and schedule.