Dharmesh’s post made me realize there’s a name for something I’ve been doing implicitly for a while—using AI to help me write better prompts. Strictly speaking, that’s AI-assisted prompt refinement. There’s a closely related idea called metaprompting—writing prompts that generate other prompts—which also makes a real difference, especially for deeper research.
These omniscient models have been trained on nearly everything ever written, and prompts are how we tap into that knowledge. With GPT-5, the average prompt clocks in at around 50 tokens (roughly 35–40 words)—so every word counts.
I built a custom GPT to refine prompts (and, when needed, to generate reusable prompts—i.e., metaprompting). It’s available here. Naturally, I used AI to help write its instructions (meta-metaprompting, anyone?). If you try it, I’d love suggestions to improve its performance.
P.S. If you want a crisp explainer of metaprompting itself, this glossary entry is good: What is Meta Prompting? (AI21 Labs).