Repl.it is so hit or miss for me, and that's that is so frustrating. Like, it can knock out something in minutes that would have taken me an afternoon. That's amazing.
Then other times, I go to create something that is suggested _by them below the prompt box_ and it can't do it properly.
The fact that you think it was suggested _by_ them is I think where your mental model is misleading you.
LLMs can be thought of metaphorically as a process of decompression, if you can give it a compressed form for your scenario 1 it'll go great - you're actually doing a lot of mental work to arrive at that 'compressed' request, checking technical feasibility, thinking about interactions, hinting at solutions.
If you feed it back it's own suggestion it's no so guaranteed to work.
I don't think that the suggestions in the prompt box are being automatically generated on the fly for everyone. At least I don't see why they would be. Why not just have some engineers come up with 100 prompts, test them to make sure they work, and then hard-code those?
I would hope the suggestions in the prompt box are not being automatically generated by everyone else's inputs, I know what matters most is not the idea but execution but in the off hand you do have a really great and somewhat unique idea you probably wouldn't want it to be sent out to everyone who likes to take great ideas and implement it while you yourself are working on it.
You're misunderstanding me. Underneath the prompt box on the main page are suggestions of types of apps you can build. These are, presumably, chosen by people at the company. I'm not talking about things suggested within the chat.
Then other times, I go to create something that is suggested _by them below the prompt box_ and it can't do it properly.