You don't need to loop with the LLM multiple times - after a couple of prompts and adjustments you can accept the suggested code and make any modifications you want yourself because at that point editing the code by hand would be faster and more precise that expressing every detail to the LLM in English.

That way you're gaining productivity from the all the code generation the LLM does for you and you have final say on all the committed code, it seems like a win-win.