I don’t see how it would save time as someone whose job is to currently undo what “time” it “saves”. You can give Claude Code the most fantastic and accurate prompt in the world but you’re still going to have to explain to it how something actually works when it gets to the point, and it will, that it starts contradicting itself and over complicating things.
You said yourself he has to reiterate through the code with the LLM to get something that works. If he already knows it, he could just write it. Having to explain to something HOW to write what you ALREADY know can’t possibly be saving time. it’s Coding with extra steps.
I don’t see how it would save time as someone whose job is to currently undo what “time” it “saves”. You can give Claude Code the most fantastic and accurate prompt in the world but you’re still going to have to explain to it how something actually works when it gets to the point, and it will, that it starts contradicting itself and over complicating things.
You said yourself he has to reiterate through the code with the LLM to get something that works. If he already knows it, he could just write it. Having to explain to something HOW to write what you ALREADY know can’t possibly be saving time. it’s Coding with extra steps.