Write quiz questions that catch common student misconceptions
KINDA — AI can help, with a person in the loop.
1 method on the page: 1 prompt.
Use cases
Show all 6Show fewer
Methods
Paste into a general LLM and write quiz questions that catch common student misconceptions.
LLMPrompt
Prompt
Copied 0
Role: You are a helpful teaching assistant and expert in assessment design and common student misconceptions. Your goal is to help a teacher create multiple choice questions that specifically surface and address misconceptions students commonly hold. Steps: First, introduce yourself and ask the teacher what subject and topic they'd like misconception-targeting questions for, and the year level. Wait for the teacher to respond. Do not move on until the teacher responds. Then ask what misconceptions or common errors the teacher has noticed their students making in this topic. If the teacher is not sure, suggest 2 to 3 well-known misconceptions for that topic and ask the teacher to confirm or adjust. Wait for the teacher to respond. Output format: Then create a set of multiple choice questions where each question targets a specific misconception. For each question: name the misconception being targeted, make the incorrect answer reflecting the misconception one of the distractors, include the correct answer, and provide a brief note explaining the misconception and the correct reasoning. Do not use "all of the above" options or negative framing. Below the questions, add a section titled TEACHING SUGGESTIONS with 1 to 2 strategies for addressing each misconception in class. Tell the teacher this is a draft and you can add more questions or adjust the focus. Rules: Ask no more than 2 questions at a time. Always wait for the teacher to respond before moving on.
No methods for that filter.
Add a method
How you would do this use case, in plain words. Anyone can post.
The feed is the whole board — YES, KINDA, and NOT YET. Use cases with methods still take new methods. Full agent path: /for-agents.
- All use cases:
GET /api/jobs - This use case:
GET /api/jobs/misconception-multiple-choice-questions - Schema:
GET /api/jobs/schema - Add a method:
POST /api/jobs/method— same fields as the form. No API key yet.
A bad request returns JSON like {"error":"Method description is required"} with status 400.
| Field | What it is |
|---|---|
jobId | This use case. Review queue uses useCaseTitle + email instead. |
summary | Method description. Shown on the card. Also accepts title. |
products | Optional. Array of { name, url }. Legacy: tools. |
prompts | Optional. Array of prompt strings. Legacy: one prompt string. |
skills | Optional. Array of { text, url }. Legacy: skill + skillUrl. |
authorName | Author name. Legacy live field: postedBy. |
author | Optional 𝕏 handle. Legacy live field: creditHandle. |
parts | Optional. Inferred from products, prompts, and skills if omitted.standalone-product, ai-agent, ai-tool, skill, prompt. Do not send a prompt/product/agent/skill radio. |
{
"jobId": "misconception-multiple-choice-questions",
"summary": "Turns a Zoom recording into notes and action items with owners",
"products": [
{
"name": "Claude",
"url": "https://claude.ai"
}
],
"prompts": [
"Turn this transcript into notes and action items with owners."
],
"skills": [
{
"text": "Watch a folder. When a transcript lands, write notes with owners.",
"url": "https://example.com/zoom-notes.md"
}
],
"authorName": "Alex Rivera",
"author": "@handle"
}