AI Built His Restaurant App in a Day. Then He Asked Me to Host It.
Vibes Don't Maintain
A restaurant owner with no coding experience built a staff task app using Claude Code and asked the author to host it. It looked clean but had no login, no responsive layout, no error states, and no handling of edge cases—a click-dummy, not a system. The piece argues AI makes execution cheap but doesn't teach you what to build or how to keep it running when something breaks.
Software is mostly seatbelts. The happy path - the thing the demo shows - is the smallest part of the codebase.
- BubbleRings
> "...or the parts that have never once executed in production because they’re there for a worst case someone sat down and imagined."
Good stuff.
> "It’s the record of what the code was supposed to do ... written down somewhere a human or an agent can read them back. Ours are markdown files in git..."
I keep getting surprised how many quite technical people I know are doing real work with AI but have never touched markdown.
If you are one of those people, allow me to offer a suggestion:
Stop. No more sending questions to ChatGPT or Claude until you do the following:
- Install Typora on your Windows or Mac machine.
- Write a .md (markdown text) file a full page long using Typora (or another editor that understands markdown, but Typora will do just fine). Make use of Heading 1, Heading 2, and underline formatting, at least.
- Make the one page file be a complex request to an AI. Something like "research x, compare it to y, make a guess what will happen in the future, here are some of my opinions and guesses, make your replies short, provide references".
Hand that .md file to your favorite AI. (Bonus points for using drag and drop or pointing the AI at the dir the file is in.) Look at your results. Make a change to your .md file. Hand it to the AI again, see the different results.
In my opinion, if you work on a keyboard and you've been making use of AI for the last 8 months, you should have done the above 4 months ago. Until you do, you will have a hard time understanding how d […]
- Vishal_Max
This aint completely true anymore but i do agree to the fact that , ai cant reliably build the entire app in one shot or within couple of days, and also you can expect the same bug from a dev himself, even big teams do make mistakes and leave out edge cases.
- erelong
I get the point but it seems overstated: when the app breaks, they'll ask AI to maintain it (with varying results) and in the first place they can ask AI to do checks to catch some things in advance that they might need
what's also ironic to me is a lack of templates for pro or am alike to follow along with (whether using AI or not), like the list of possible problems that could pop up... a lot of those could probably be handled in a template or like checklist (with AI assistance)
- DonsDiscountGas
Decent points, but at this point if the restaurant owner could articulate their needs at a non technical level, I bet Claude or Codex could do a good job. Which is harder than it sounds but not exactly rocket science:
* Make an app for scheduling shifts for my staff.
* Needs to handle multiple users with intelligent reconciling of edits
* Needs to adapt to both English and Spanish speakers.
* Needs authentication
* Need 99.9% reliability
This gets most of the way there. Presumably the restaurant owner will need to iterate, but isn't that always the case? Iterating now doesn't require hiring external help.
- fk202611
I can only read code at a basic level, so I am in the same position as the author of this article.I built a diagnostic app using AI. With my initial prompt, I was able to get it to generate diagnostic results.However, when I ask AI to make changes, something else sometimes breaks. Every time this happens, I have to ask AI to check the code again.