TJP

Vibe Coding: Using AI to Turn an Idea Into a working App?


12.01.2026 – Author:

Let's be honest: I've subscribed to a fitness app for years – and used it far less than I wanted.
All it really did was save my previous weights and set a timer. For years, I told myself I'd use it more. I didn't.
There had to be a better way.

Here's what I realized:
AI makes building software easier than ever. But let's not be naive – "garbage in, garbage out" still applies. The magic isn't in the AI itself; it's in how you guide the process.

So I turned my frustration into a learning project:

I wanted to experience the full cycle of AI-assisted app development firsthand. From the first idea to feature conception, user journeys to App Store rules, distribution to marketing – all of it.

The result just entered the android app store → SetLog: Simple Gym Tracker

A simple, focused, and completely ad-free gym tracker that does exactly what I actually needed: Track sets, reps, and weights. See my progress. Remember my last values automatically.

That's it.

No social feeds. No premium plans. No overloaded menus. Just training data, clearly structured.

What I learned along the way:

AI is a powerful co-pilot, but you still need to steer (otherwise you will create generic AI slop)
The AI-assisted design process is upside down – "let the AI start and iterate on that to only keep what you need" became the guiding principle
Combination of different tools is king – e.g. lovable for the base, bolt.new for everything that isn't react code and copilot/claude for the finetuning

The app is free and ad-free. But honestly? The real value was in the process itself.



Back to Overview

Drop me a message!