I'd like my colleague - who submitted 19 LLM generated markdown files for review - to submit the prompt for review instead of the output. That's the human part, the rest is just LLM generated word vomit listing all the implementation details. These might be important for another LLM to write the implementation, or to use as inspiration to split up the task into subtasks for humans, but it's not for me. Humans wouldn't go into that much detail speccing out software.