How to write good prompts

Found a good [blog post]( about creating good prompts. - Retrieval practice prompts should be **focused**. ... one detail at a time - Retrieval practice prompts should be **precise** about what they’re asking for. Vague questions will elicit vague answers, which won’t reliably light the bulbs you’re targeting. - Retrieval practice prompts should produce **consistent** answers, lighting the same bulbs each time you perform the task. Otherwise, you may run afoul of an interference phenomenon called **retrieval-induced forgetting**. This effect has been produced in many experiments but is not yet well understood. For an overview, see Murayama et al, Forgetting as a consequence of retrieval: a meta-analytic review of retrieval-induced forgetting (2014).: what you remember during practice is reinforced, but other related knowledge which you didn’t recall is actually inhibited. - Retrieval practice prompts should be **tractable**. you should strive to write prompts which you can almost always answer correctly. This often means breaking the task down, or adding cues. - Retrieval practice prompts should be **effortful**. _Factual Prompt_: What type of chicken parts are used in stock? -> Bones. _Explanation Prompt_: Why do we use bones to make chicken stock? -> They’re full of gelatin, which produces a rich texture. _more precise_: How do bones produce a chicken stock’s rich texture? -> They’re full of gelatin.


_Grouping_: Chicken stock is made with chicken, water, and what other category of ingredients? -> Aromatics. _Missing Element_: Typical chicken stock aromatics: - ??? - carrots - celery - garlic - parsley A: Onion Tip: keep the list in the same order [visual “shape”]. > Most spaced repetition software has a special function which can rapidly > generate sets of fill-in-the-blank prompts like this. In the software > interfaces, these prompts are often called “cloze deletions.” In each review > session, the software will only ask you to fill in one blank. This behavior > is important because without it, one variant would “give away” the answer to > another. _explaination prompt_: Why is carrot a good aromatic for chicken stock? -> A quick answer: carrot provides vegetal sweetness; like salt, this sugar brightens other flavors. _elaborative encoding_: Typical chicken stock aromatics: - onion - carrots - celery - garlic - ??? (herb) A. Parsley _bad: gives away too much_: Typical chicken stock aromatics: - onion - ??? (rhymes with parrots) - celery - garlic - parsley A. Carrots _elaborative encoding_: Typical chicken stock aromatics - onion - ??? - celery - garlic - parsley A. carrots (rhymes with “parrots”: picture a flock of parrots flying with carrots in their mouths, dropping them into a pot of stock) _prompt to Mnemonic_: Mnemonic device for carrots in chicken stock? -> rhymes with “parrots”: picture a flock of parrots flying with carrots in their mouths, dropping them into a pot of stock > Notice how I’ve broken the ingredient list down into many questions here, each > focused and precise. I’ve noticed that people often feel a compulsion to > economize on the number of prompts they write. Prompts seem to carry a > per-unit “price,” so people naturally try to write fewer questions which cover > more ground. But that’s counter-productive. Unless you explicitly decide to > exclude certain information, the number of “units of raw knowledge” is fixed, a > constant of the territory. When you write coarser prompts in smaller quantity, > you’re not reducing the amount you have to learn. You’re just making the > material harder to review. > write more prompts than feels natural.