Hire an AI classroom AI reliability lesson planner

Everything it can hand back

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

• Lessons on where AI answers go wrong and how to check them
• A spot-the-mistake activity built from a real AI answer
• A lesson where students critique an AI answer against a rubric
• Your assignment's AI rules checked and rewritten to be clear and fair

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: Your students hand in AI answers with confident errors in them.

• Step 1: Reliability lessons. Lessons on where AI answers go wrong, with an example from your subject, how to check, and a question to test understanding.
• Step 2: Mistake hunt. A real AI answer, a student worksheet, and an answer key listing each mistake and how to check it.
• Step 3: Critique lesson. A rubric, a task where students grade an AI answer, a task to write the better version, and discussion questions.
• Step 4: Assignment rules. What was vague or unfair, what is allowed, what is not allowed, and how students show their own work.
• HAND-BACK SUMMARY. Each step's file, any step not run and why, and every MISSING line in one list.

How the work is checked

• Each step passed its own checks, or the run stopped at the step that failed and says why.
• The steps ran in order, and each one used the result of the one before.
• Nothing was invented to fill a gap. Every gap is a MISSING: line.
• Nothing was sent, published or paid for without a clear yes.
• 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

• Plan the reliability lessons. Plans lessons on where AI answers go wrong and how to check them, with examples from the subject.
• Build the mistake hunt. Builds an activity where students find mistakes in a real AI answer, with a worksheet and answer key.
• Plan the critique lesson. Plans a lesson where students grade an AI answer against a rubric and write the better version.
• Fix the assignment rules. Checks your assignment's AI rules for vagueness and unfairness and rewrites them so students know what is allowed.

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 teach-a-class-to-check-ai-answers-and-set-fair-ai-rules 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/teach-a-class-to-check-ai-answers-and-set-fair-ai-rules/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 subject, the age group and what they already know
• An assignment you set, with its current AI rules if any
• A real AI answer on the subject, or let it produce one to work from (optional)
• How many lessons you can give to this

Helpful context (optional)

• Your school's AI policy
• Past student work with AI errors in it
• Your marking rubric

Tools and access

• Any good chat AI: Every step is a plan or a piece of writing.
• Your class's chat AI: Students need the same tool in class that they use at home.

Functions and deliverables

• Classroom AI reliability lesson planner: Share the subject, student age and task. Get AI answer checks, a mistake-hunt worksheet, an answer key and clear rules for class.
  • Lessons on where AI answers go wrong and how to check them
  • A spot-the-mistake activity built from a real AI answer
  • A lesson where students critique an AI answer against a rubric
  • Your assignment's AI rules checked and rewritten to be clear and fair
• Cross-subject AI reliability lesson planner: Share two or more subjects and the student level. Get lessons for comparing AI answers, their evidence and the kinds of claims they make.
  • A note on how each subject builds knowledge
  • Matching questions for each subject
  • A comparison and recording protocol
  • A reliability framework and discussion guide
  Source: Gareth Manning.
• AI error detection lesson planner: Plan a classroom activity where students catch what AI gets wrong about a subject they know well. Name the topic and age group to start.
  • A step-by-step student activity
  • Question prompts for the AI
  • A checklist of error types to look for
  • A discussion plan
  • Reflection questions
  Source: Gareth Manning.
• AI answer review worksheet builder: Share an AI text sample and class level. Get marking steps, a scoring guide, questions and a teacher example for checking it.
  • A markup guide for students
  • A weak, moderate, strong scoring grid
  • Sentence starters for pushing back
  • A teacher modelling script
  Source: Gareth Manning.
• Assignment AI-use rules planner: Share an assignment and learning goals. Get rules for each part, showing where AI may help and where students need practice.
  • A map of each part rated for AI use
  • A clear student-facing rule
  • Search versus AI guidance (optional)
  • Redesign ideas for weak spots
  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

• Your students hand in AI answers with confident errors in them.
• Your school asked for an AI policy and nobody knows what to write.
• You want students to use AI as a tool and still learn the subject.

Limits to check before starting

• You need one lesson and have no assignment to check: use a plain worksheet and write the lesson yourself.
• You only need a school-wide AI policy: ask your head of department or use your school's policy template.
• You want to grade student work: use the Student marking and feedback reviewer workflow.

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 a HANDOFF.md file and the skill files this workflow uses.
• Open Claude, ChatGPT or Gemini and add the files from the zip. Say "Follow HANDOFF.md". Claude Code or a Claude Project handles files best.
• Paste the subject, the age group, your assignment and how many lessons you have.
• Read the answer key for the mistake hunt. Check each mistake yourself before you teach it.
• Read the rewritten AI rules. Fix anything that does not fit your school, then add them to the assignment.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/teach-a-class-to-check-ai-answers-and-set-fair-ai-rules 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.