Write feedback on student work faster without letting AI grade it
KINDA — AI can help, with a person in the loop.
1 method on the page: 1 agent.
Use cases
Methods
Use AI to draft feedback on work you have already graded
Institution-approved AI assistant
Steps
- Mark the work yourself against the rubric, decide the grade and jot down strengths and what needs improving; the AI plays no part in grading.
- If you want help with wording, write a short summary of the work that leaves out anything identifying the student.
- Give that summary and the rubric criteria to an AI assistant your institution approves and ask it for a draft of constructive feedback.
- Edit the draft for accuracy and tone, add concrete examples from the student's own work and make it sound like you.
- When you are happy with it, paste it into your learning platform and release it as usual, taking responsibility for it as your own.
- Optional: The source also offers three feedback prompt templates; they are linked there, not copied here.
- Note: The steps are kept as published, in our own words. James Cook University wrote them for its staff using Microsoft Copilot signed in with university credentials; here that is generalised to an AI assistant your institution approves. Follow your own institution's rules on AI and student data. Repeat for each assessment you grade.
Run this method with your agent
Download .mdCopied 0
--- name: "ai-assisted-feedback-on-student-work-method" description: "Use when you need to Write feedback on student work faster without letting AI grade it. Use AI to draft feedback on work you have already graded" --- # Use AI to draft feedback on work you have already graded Job: [Write feedback on student work faster without letting AI grade it](https://aiagents.org/canai/ai-assisted-feedback-on-student-work) ## Need - ai agent: [Institution-approved AI assistant](https://aiagents.org/agents/institution-approved-ai-assistant) ## Steps 1. Mark the work yourself against the rubric, decide the grade and jot down strengths and what needs improving; the AI plays no part in grading. 2. If you want help with wording, write a short summary of the work that leaves out anything identifying the student. 3. Give that summary and the rubric criteria to an AI assistant your institution approves and ask it for a draft of constructive feedback. 4. Edit the draft for accuracy and tone, add concrete examples from the student's own work and make it sound like you. 5. When you are happy with it, paste it into your learning platform and release it as usual, taking responsibility for it as your own. 6. Optional: The source also offers three feedback prompt templates; they are linked there, not copied here. 7. Note: The steps are kept as published, in our own words. James Cook University wrote them for its staff using Microsoft Copilot signed in with university credentials; here that is generalised to an AI assistant your institution approves. Follow your own institution's rules on AI and student data. Repeat for each assessment you grade. ## Credit Method author James Cook University Source: https://www.jcu.edu.au/ai-at-jcu/ai-for-staff/ai-guides-ai-for-feedback
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/ai-assisted-feedback-on-student-work - 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": "ai-assisted-feedback-on-student-work",
"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"
}