This is entirely possible. But here's my thesis; "Things that are trivial to do, are often done." I know sounds like a tautology but think about it, even things that aren't particularly trivial are done too, just for fun. And people do them and post them to share them with others. But when things are "hard" to do, then when someone does them they have of sense of "I worked hard to make this work, I'm not gonna just let anyone have it." sort of thing. Not always, but also not uncommon.
So elsewhere in this set of comments is a comment by someone who said they had vibe coded a work alike. Several other people responded that they too vibe coded work alikes. Is my mental model so out of date that nobody actually posts that work? So let's presume for argument that 'prompts' are the new source code. Why doesn't someone share, "This is the prompt I used with model <x> and it produced a Harvest work alike:" ? Even better would be "This is the prompt I used and this is all the code it generated and how it can be built into a Harvest work alike." But has anyone shared anything like that? If not, why not?
My thesis is that one possible reason[1] for it not being done, is because people didn't actually do it. I do not doubt that people believe strongly that it could be done, but belief only goes so far, Its the putting that belief into practice that reveals the challenges that perhaps were overlooked. I have definitely had that experience where I believed I could do something easily only to find it was harder to do than I had imagined. No judgement there, it happens all the time.
What I have observed is that when you don't see a lot of copies popping up of some system that should be "easy" to reproduce, is that there is some complexity buried in that system which makes producing it "hard" and people stop trying before getting over the hump to having done the thing.
So if you think this software can be easily vibe coded, then by all means educate me by showing me how easily you've reproduced it with a few prompts. It would really help me update my world view.
[1] Not the only reason, just one that fits the evidence.
Occam's razor. What's more likely, it isn't trivial to do or multiple independent people telling an unfalsifiable lie about something they did that they feel increases their own cool factor.
Lots of comments on this thread about how 'easy' it is to create a replacement but nobody can point to a repo that replaces it? No front page story "I made a Harvest Alternative with AI and got a 'cease & desist'", there is even a comment made that google searches for 'Harvest Alternative' have skyrocketed. So which is more likely? I don't know.
My observation is that if people haven't done a thing, that is a desirable thing to do, that seems 'easy', then it is either not desirable or not easy.
I really do like to be proved wrong though, just one-shot a replacement, point me at the repo and tell me how you validated it to be functional. Because that is easy it shouldn't take much time, heck probably less time than it took for me to type all this.
Now there has always been software that people have used that they "could" write for themselves but they didn't because they didn't want to maintain it. Seems like things that are like that would be good candidates for this right?
But this question shares at least a spiritual geneology with the response to some new startup code that does some thing, and the comment here is "Gee, I can't believe that got this funded, I could write that in a weekend."
The problem is, there are many things that are easy to describe but difficult to pin down, and reality is complicated. So many times I've gone into a project thinking it would be "easy" only to start uncovering layer after layer that are much more involved than I expected.
So no, you cannot '1-shot prompt' pretty much any significant software, and that goes doubly true if it affects your life in any potentially devastating way.
One of the things I'm constantly amused by[1] is the Solitaire program on iOS that is clearly being vibe coded these days because it comes up with daily challenges like 'win a hand in -2739551 moves'. Like no human would ever write code that screwed up basic math but LLMs do it all the time.
[1] Obviously I am easily amused :-). But it is sort of the 'pelican riding a bike' test where you can easily tell what a human would do vs what an LLM does.
[2] EDIT: another commentator says they vibe coded it in a weekend. That would support the hypothesis that the application could be at lease a small number of shots vibe coded. That said, I'd love to see that code and the prompts that led to it.