Vibecoding
Build for the vibe, debug later
Start new thread
Meir Davidov

Just quoted a client $43k to fix what AI built in 3 hours

by•

Had a fascinating discovery call yesterday. Founder showed me their SaaS - built entirely with Cursor in one weekend. Stripe payments, auth, admin panel. Actually works great, they're at $11k MRR.

Then they opened the codebase.

Same Stripe webhook handler copy-pasted 8 times with tiny variations. Zero architecture. AI did exactly what it was told - perfectly isolated features that never talk to each other.

Here's the kicker: GitClear's data shows code churn hit 7% in 2025 (highest ever). Translation - we're adding code faster but reusing it way less. One startup they tracked has 510k lines that's 70% AI generated, and honestly this client's headed there.

The economics are wild:

  • Build MVP: 1 weekend

  • Hit $11k MRR: 6 weeks

  • Make it maintainable: $43k + 4 weeks

  • Actual problem: Can't hire devs until it's fixed

I see this pattern now in about 60% of AI-built projects I review. Not an AI problem - it's an architecture problem. Stack Overflow found 84% of devs use AI daily, but the velocity gap between clean and messy codebases just got massive.

What's working: Clients who spend 20-30 min sketching module boundaries BEFORE vibe-coding. Just boxes and arrows. Then let AI fill in the boxes. Architecture = human. Implementation = AI.

Seen this pattern with your projects? How are you handling the architecture piece?

Resources:

GitClear 2025 AI Code Quality Report

Stack Overflow Developer Survey 2025

MIT Sloan - Hidden Costs of AI Coding

If you're building something and want to discuss architecture before the AI does its thing,

connect with me on LinkedIn -

Meir Avimelec Davidov
Founder & CEO gliltech software

209 views

Add a comment

Replies

Best
Anunjay Chouhan
I think vibe coding is only good at the prototype or early MVP level. You’d have to bring in humans for scaling. That being said, I wonder if vibe coding platforms will bring in Agents who focuses more on architecture when a user is building for scale
Meir Davidov

@anunjay Exactly. Regarding agents - I wonder about it too, I think for now only developers should deal with agents since a minor mistake with it can make massive business mistakes. But I believe iin the future its definitely possible, lets see

Navam

You are observing a new "side effect" industry $$$ spawning my friend. Here are similar ones:

  1. When it was too easy to fire up cloud services in the wild, which became uncontrollable pay-per-use, the cost optimization side effect industry was born.

  2. When multiple model providers offered cost, capabilities differences, always trying to one-up the other, the multi-model-provider orchestration side effect happened (aka openrouter).

  3. Can others think of more examples?

Daniil Poletaev

Wow, that's impressive that they could go that far with a vibe coded app 🤯
I mean I can't go that far with a well tested software I spent more than a year on...