System prompts are usually written as one giant block of text, but they work better as separate, testable components. Hamel Husain and others argue for modular design: break prompts into distinct pieces like core responsibilities and guidelines, then test each one to see what actually matters.
Every time I built a prompt library, from the very first time to the most recent one I built, every single time, these things in the system prompt are components. They are components that you plug in. And I have always wanted to basically ablate each of them and say, if I ablate the part where I say core responsibilities, what happens? If I ablate ingredient guidelines, what happens? It's just a personal feeling that all of these have— probably can do because they have variables. But I still find myself wondering, why are we writing massive system prompts that are just plaintext as opposed to components?
I think it, it also is in line with the principle of have the least complexity.
