Comment by rahoulb
4 hours ago
When I quit my day job and started Rails freelancing a big chunk of my work was from companies with "that tech guy" who had built a database in Microsoft Access that was vital to the department's operations. And then either left the company - or the app had started to fall apart under its own weight.
I would get called in to rewrite it, using a proper database, documented rules and ensure it stayed scalable - and everyone would be happy.
These Access "apps" were abominations from a technical point of view - but they got the job done without having to spend a load of money on off-the-shelf or bespoke software. And the "tech guy" made a valuable contribution to the company. It's only at a certain point that Access started to struggle.
I foresee the exact same thing happening in the near future - except we won't be building the replacement apps ourselves - we'll just know how to give the coding agents well-specified prompts and tell them when they're making a mistake.
I’m at exactly that point where it sounds like you were. I’ve done 3 Access to Rails conversions and I’m hunting for the next one. The one I’m on at the moment is supporting 5 branches over 2 countries and 2 independent machine shops. Even if I can understand what Access is doing under the hood there is no one left to ask why. And I have so many questions. Sit with the users, spec the feature, ground it in whatever data I can find. I don’t think that ever changes for SMEs that take this path (Access or Vibeccess) and need re-writes. I’m also very happy to do them. They are IMO giving me more valuable usage data than any design process ever could.
What is different on this one vs the others is I have Claude to help me data dive and write the boring CRUD parts. I am able to spend so much more time with users testing and getting feedback and just thinking deeply about how to structure things. The quality of what I’m building now has never been higher and I think it’s just because I have more time to spend with it.
My experience with AI has been almost wholly positive and I wonder if Rails is part of the reason. Such well established patterns and structure the agent one shots most things and I spend most of my time wrangling view code based on my preferences.
But at least you could basically follow their logic.
I think what a lot of us are concerned about is that the vibe-coded stuff bloats fast. It's so verbose and all over the place, that picking that thing apart will be a huge job, and relying on an AI to pick apart work that an AI already failed to maintain seem like wishful thinking.
It's literally "The AI is failing! Don't worry I'll just use AI to fix the AI!".
Yes, as long as context size increase and llm improve at least there's a way out through using AI but once the progress stops...
Huh? Even if progress somehow stopped, current models are already good enough to help -- and the quality of a given vibe-coded throwaway codebase will be higher the more recently it was created.
The worst I would ever get was "here's our Access database - can you rewrite it". That was utterly useless to me.
What I needed to do was sit with a user (not a manager/the person buying my services) and ask them to show me the different things they did with the software. Then I could write a spec for the actual _feature_ and would only need to look at the existing codebase if they needed data transferring across[1]. I don't see why our new LLM-based future would be any different
[1] Of course this meant I would leave out edge-cases and/or weird quirks of the system - often this was actually a bonus as they were either no longer relevant or worked that way because that was the only way they knew how to do it