Prompt library

AI prompts for research

Reading sources, summarising, and comparing options.

What these prompts are for

Comparisons and summaries fail quietly, because what comes back is not wrong. It is fluent, balanced, accurate, and gives you no basis for choosing — a comparison written for everyone is weighted for nobody, and most of what makes two options different has nothing to do with what you are doing.

The prompts here push the differences that apply to your constraints to the front and say out loud which famous differences do not apply to you. For sources, they keep the evidence attached to the claim, so what a study establishes stays separate from what its abstract asserts.