Prompt library
Generate a quiz from course material
Distractors built from named misconceptions turn wrong answers into diagnostic data about who believes what. Requiring novel examples for application questions closes the loophole where students pass by pattern-matching the textbook's exact sentences.
Last reviewed July 17, 2026
The prompt
Create a quiz from the material below.
Material: {{material}}
Format needed: {{format}}
Rules:
1. Distribute questions across Bloom levels and label each: 30 percent recall, 40 percent application (new example, same concept), 30 percent analysis (compare, predict, find the flaw).
2. Multiple-choice distractors must each encode a specific real misconception, not filler. After each MC question, note in brackets which misconception each distractor catches.
3. Application questions must use examples NOT present in the material, so recall cannot masquerade as understanding.
4. Include one question whose correct answer is "the material does not say", to teach epistemic care. Mark it.
5. Answer key at the end, with a one-line explanation per answer and the material section it comes from.
Nothing on the quiz may require knowledge outside the material except the transformed examples in rule 3.Run in idaptOpens a new chat with the prompt prefilled. Nothing sends until you press send.
Fill in the variables
| Variable | What it is | Example |
|---|---|---|
| {{material}} | The source material | [paste the chapter or attach the file] |
| {{format}} | Question count and types | 10 questions: 6 multiple choice, 3 short answer, 1 essay |