Hire an AI student feedback and revision task planner

Everything it can hand back

Your task sets the actual outputs. The specialist picks the methods that cover them.

• A single-point rubric for the task
• Each comment checked, with a rewrite where it is vague and a note on what changed
• A short revision task aimed at the main gap, with answers where it has one
• A teacher review list of what to confirm before work goes back
• A summary of what could not be checked and one next step

How it does the job well

• Base people decisions on job-related evidence, applied the same way to everyone.
• Write in plain, respectful language the person affected could read.
• Keep personal data to what the task needs, and handle it privately.
• Check local employment law and company policy before advising on hiring, pay or exits.

Mistakes it avoids

• Biased wording in job ads, reviews or interview questions.
• Plans with no owner, timing or way to check progress.
• Treating a template as legal advice.

What a good result looks like

An example, not your task: You have a stack of drafts and your comments are mostly "good, but more detail".

• Single-point rubric. One standard for the task, with space to note gaps and evidence.
• Checked feedback. Each comment with its problem, a clearer rewrite and why it changed.
• Revision task. A short task aimed at the main gap, with answers or marking notes.
• Teacher review list. What you should confirm yourself before any feedback goes back to a student.
• Hand-back summary. Files saved, facts missing, checks not done and one next step.

How the work is checked

• Every rewritten comment points to one criterion and names one next step.
• No comment states something that is not in the work.
• The revision task targets the one gap, and its answers were checked.
• No student name or grade appears in any file.
• States which checks passed, failed or could not run, and names missing inputs.

These checks have not been run against a model yet. Your AI uses them to check its own work.

Capabilities

• Single-point rubric builder. Turns your goal into one clear standard with space for evidence and notes. It hands the standard to the comment check.
• Written feedback checker. Checks each draft comment against that standard for specificity, accuracy and a next step, and rewrites the weak ones. It hands the main gap to the task step.
• Practice problem set writer. Writes a short revision task for that gap and checks the answers and difficulty. It hands the task to the teacher review list.

How the role works

1. Checks your task, context and available tools.
2. Picks the methods needed and prepares a work plan.
3. Carries out supported tasks, with each method's limits and review gates.
4. Checks the real deliverables and corrects supported faults.
5. Hands back files, evidence and unresolved gaps.

Your specialist's working setup

Download the base specialist without a task form or account. README.md and SETUP.md explain how to use the folder. SOUL.md defines its scope. INTAKE.md asks missing questions inside your AI. PLAYBOOK.md, SKILLS.md, BEST_PRACTICES.md, CHECKS.md and HANDOFF.md guide the work and its checked deliverables.

Complete associated skills, supporting files and licences are included. Choose only the methods needed for the actual task. Keep context, working files and accepted feedback in your AI project.

Use this specialist through MCP or the API

Call prepare_specialist with role_id prepare-feedback-students-can-act-on only. No task is required to load it. Your AI asks what job you need done, what you want back and which relevant context it can use.

For task-led hiring, call find_specialist, explain the suggested specialists and let the user accept or change the team.

Complete ZIP: Download base specialist. API: GET /api/v1/specialists/prepare-feedback-students-can-act-on/pack. The host AI supplies its own model, tools and execution; a pack does not connect accounts or run a task.

Inputs and helpful context

The specialist starts from the task brief. Only active methods require their inputs.

For the primary method, when used

• The task students did and what it is meant to teach
• Your rubric, success criteria or learning goal
• A piece of student work, with the name and other personal details removed
• The comments you plan to give
• The year group or level
• Your own rules for feedback, such as one next step only (optional)

Helpful context (optional)

• Two or three more pieces of work, to see whether the same gap repeats.
• A strong example from a past class.

Tools and access

• Claude, ChatGPT or Gemini with file support: They can read pasted work and your rubric. Check your school's rules before pasting student work.

Functions and deliverables

• Student feedback and revision task planner: Share the task, marking guide, student work and draft feedback. Get clearer feedback, a focused practice task and teacher review points.
  • A single-point rubric for the task
  • Each comment checked, with a rewrite where it is vague and a note on what changed
  • A short revision task aimed at the main gap, with answers where it has one
  • A teacher review list of what to confirm before work goes back
  • A summary of what could not be checked and one next step
• Single-point rubric builder: Share a learning goal. Get a one-criterion rubric with open columns for evidence, ready for feedback or self-assessment.
  • One clear criterion statement
  • A three-column rubric with open evidence columns
  • A version for the stated purpose
  Source: Gareth Manning.
• Written feedback checker: Paste feedback given to learners. Get a check for how specific and useful it is, with better wording.
  • A level-by-level diagnosis of each comment
  • A check on specificity, threat and next step
  • A rewritten version of the feedback
  • A short list of habits to change
  Source: Gareth Manning.
• Practice problem set writer: Share a skill, student level and problem count. Get a practice sequence with fewer hints over time and notes for teachers.
  • Ordered problem set
  • Difficulty levels labelled
  • Answer key
  • Notes on common mistakes
  Source: Gareth Manning.
• me.md builder: Answer a few questions, or let your AI use what it remembers. Get one private file that tells any AI who you are.
  • One me.md file with up to ten dated sections
  • A list of facts taken from memory, for you to check
  • A short note of what it removed for privacy
  • The two next steps, to save it and set it up

Tasks you can use it for

• You have a stack of drafts and your comments are mostly "good, but more detail".
• Students read your feedback and then make the same mistake in the next piece.
• A colleague wants a second look at their comments before work goes back.
• You want feedback tied to a clear standard before a student redoes the work.

Limits to check before starting

• You need a batch of work marked against a rubric. Use the Student rubric feedback writer.
• You need a full marking grid with a level for each criterion. Use the Marking rubric writer.
• You only want to check comments you already wrote. Use the Written feedback checker.
• The feedback comes from an AI tutor. Use the AI feedback quality checker.

Best way to use this role

Give it one clear outcome, the actual files and a definition of done. Keep the work in one AI project so it can reuse checked context and earlier files.

• Download the handoff pack. It is a zip with HANDOFF.md and every skill file this workflow uses.
• Give the folder to Claude, ChatGPT or Gemini and say "Follow HANDOFF.md".
• Paste the task, your rubric or goal, one piece of work with the name removed and your draft comments.
• Read the rewritten comments. Keep your own voice, and change any line that is not true to the work.
• Give students the revision task with the feedback, and check the answer key before you do.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/prepare-feedback-students-can-act-on for its role instructions and pinned sources.

This is a prepared AI role. No task has run. Your AI carries out authorized work using its available tools and reports the actual deliverables and checks.