In the article (link below) the author vibe-coded a full-stack React “todo” app with an Claude Code and had it live on the internet in under 90 seconds — including frontend, backend, database, REST API, Swagger docs, and deployment — without writing a single line of code by hand.
The key takeaway isn’t just the speed. What made the rapid turnaround possible was the stack itself: a low-ceremony platform (Codehooks.io) that keeps frontend and backend together, avoids CORS and infra config, and uses schema-driven APIs so the AI doesn’t get stuck on peripheral problems.
Instead of AI nirvana, the article argues we should be thinking about what stacks maximize AI productivity — the ones that remove friction points and keep the feedback loop tight between idea and deployment.
One of the frustrating aspects of using prompts to generate code is that the output can vary quite a bit even with the same prompt. Creating an API which use the OpenAI APIs for mission critical solutions feels a bit scary and unpredictable. For structured output, I know people use libraries like Pydantic with Python. I don't now the best approach to deal with this with regards to code generation, though. For now, I guess having an experienced software engineer examine the code is essential.
Increase the limit to something useful. Using your example of a contacts database, being limited to 100 records means I can't use your service to run my app for more than a month. Plus, as a side project it'd take me longer than that just to get it working.
Time limits put people off because you can't run a small project on the service, so any time you invest in learning it is going to be wasted if you can't/won't pay later on.
I actually really like IBM's Cloudant model where they change incrementally for everything but don't bill you if your usage for a month is under $50. That way I can happily build a small side project knowing it'll only cost me if it gets moderately big.
The key takeaway isn’t just the speed. What made the rapid turnaround possible was the stack itself: a low-ceremony platform (Codehooks.io) that keeps frontend and backend together, avoids CORS and infra config, and uses schema-driven APIs so the AI doesn’t get stuck on peripheral problems.
Instead of AI nirvana, the article argues we should be thinking about what stacks maximize AI productivity — the ones that remove friction points and keep the feedback loop tight between idea and deployment.
Link: https://dev.to/restdbjones/i-vibe-coded-a-full-stack-react-a...