DEV Community

Cover image for A 1-hour experiment: vibe-coding an app to break the ice at a networking event

A 1-hour experiment: vibe-coding an app to break the ice at a networking event

Julien Avezou on March 20, 2026

It’s 5pm. My event starts in an hour. Plenty of time to build an app, right? I’m currently exploring a new project idea. Still early, still m...
Collapse
 
itsugo profile image
Aryan Choudhary

I love this idea, Julien! Breaking the ice with a fun game like that must have been a great way to get people talking. I've seen how hard it can be to start conversations at events, so kudos to you for finding a creative solution - it's really very inspiring.

Collapse
 
javz profile image
Julien Avezou

Thanks Aryan! It did make the event more fun for me :)

Collapse
 
itskondrat profile image
Mykola Kondratiuk

I did something similar at a local hackathon - threw together a quick randomizer for team forming in like 45 min and people were actually using it during the event. Honestly that immediacy is the whole point. I think vibe coding just works differently when you are building for a room full of people right in front of you, the feedback loop is instant and keeps you honest about what actually matters.

Collapse
 
javz profile image
Julien Avezou

Nice to hear! That sounds like a great use case for vibe coding too.

Collapse
 
leob profile image
leob

Interesting to read how you approached this: doing the ideation in ChatGPT, but also having ChatGTP generate the prompts for Codex!

Maybe/probably this works well because both tools (ChatGPT and Codex) are from the same company (OpenAI) ?

Collapse
 
javz profile image
Julien Avezou

Yes I am sure there are many synergies there.
The combo works well because it plays on each other's strengths:
ChatGPT is a better prompt compiler and Codex performs best when given clear, specific instructions.
This is why I use ChatGPT for thinking and Codex for building.

Collapse
 
leob profile image
leob • Edited

Yeah I found that illuminating, pretty simple approach but seems to work well !

I like it when I see these simple tricks/patterns/rules of thumb within the "AI Coding" debate, rather than very complex and esoteric setups with MCP and whatnot, which are often hard to set up or to get working well - approaches which aren't complex or "high tech", but which are practical - call it "out of the box" thinking ...

Thread Thread
 
javz profile image
Julien Avezou

I agree! I am tinkering and fine tuning as I go along, but this setup has been working nicely in the past weeks for me when it comes to prototyping and side projects.
I have used Claude in the past at my previous company but I was curious to try Codex to compare. Both feel similar. I noticed Claude tends to think longer and is better at big architectural changes.
Codex tends to execute faster, hence feeding it multiple scoped and clear prompts works best. They also released Codex Spark which is lower latency, very fast and convenient for quick troubleshooting and iterating on smaller changes. So I would make the bigger architecture changes with Codex and switch to Spark for simpler tasks.

Thread Thread
 
leob profile image
leob

The whole AI Coding thing is itself becoming an area of expertise, but the problem is that things change so fast, so when you're an "AI Coding Expert" it should be more about the abstract problem solving skills than about memorizing facts about tools X, Y or Z - because that detailed knowledge can be outdated in a month ...

It just requires an open mind an a willingness to experiment.

But yeah, Claude Code is known for its ability to "go deep" on architecture.

Thread Thread
 
javz profile image
Julien Avezou

Very true!

Collapse
 
ceopro profile image
Promise

This is cool. We actually built the thing. firstmove.live

It definitely is a key challenge to solve

Collapse
 
javz profile image
Julien Avezou

Wow very cool! Nice features. Curious: what kind of challenges do you prompt the users with?

Collapse
 
ceopro profile image
Promise

So it usually depends where you are, all challenges are contextual.

Collapse
 
amitpandey profile image
Amit Pandey

Loved this - a great example of using “vibe coding” for quick, real-world experimentation. Perfect reminder that not every app needs to be polished to be valuable.

Collapse
 
javz profile image
Julien Avezou

Exactly! I love how vibe coding allows for super quick feedback loops.

Collapse
 
ai_made_tools profile image
Joske Vermeulen

Nice experiment!

Collapse
 
javz profile image
Julien Avezou

Thanks Joske!