How I Use Claude Code
Based on my experience, Boris Tane has sensible advice here on how to leverage an LLM as a tool in your workflow creating software:
Read deeply, write a plan, annotate the plan until it’s right, then let Claude execute […]
That’s it. No magic prompts, no elaborate system instructions, no clever hacks. Just a disciplined pipeline that separates thinking from typing
Research, plan, do all the creative work. Then, as a last boring step, execute.
By the time I say “implement it all,” every decision has been made and validated. The implementation becomes mechanical, not creative. This is deliberate. I want implementation to be boring. The creative work happened in the annotation cycles. Once the plan is right, execution should be straightforward.
I think this is good advice, regardless of who is writing the code — you, a teammate, or an LLM.