Hire an AI worked-example practice sequence builder

Everything it can hand back

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

• A staged sequence: a full model, problems with fading steps and problems to solve alone
• Comparable problems with worked answers and a note on how hard each one is
• A short understanding check that asks why, with a feedback line for each likely wrong answer
• A rule for what to practise next after each kind of mistake
• A summary of what was not 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 taught a method and students nod, then cannot start the homework.

• Practice sequence. A full model, completion problems with fading steps and independent problems, with the reason for each fade.
• Problems and answers. Comparable problems at rising difficulty, each with a worked answer.
• Understanding check. Why-questions with the right reasoning and a feedback line for each likely wrong answer.
• Next practice rule. For each kind of mistake, what learners should practise next.
• Hand-back summary. Files saved, checks not run with real learner answers and one next step.

How the work is checked

• Stage 1 is the teacher's own example, and every step in it was checked.
• Every answer was worked through, and each problem uses the target skill only.
• Support fades from stage to stage, with no jump the learners have no way to make.
• Why-questions test reasoning, not recall of the steps.
• 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

• Worked example to practice sequence builder. Splits your example into a full model, completion problems that fade the help and independent problems. It hands the stages and the target skill to the problem step.
• Practice problem set writer. Writes comparable problems at rising difficulty and checks each answer. It hands the problems and answers to the check step.
• Study understanding check. Writes why-questions and a feedback line for each likely wrong answer. With real learner answers, it checks the reasoning and chooses the next practice.

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 turn-a-worked-example-into-independent-practice 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/turn-a-worked-example-into-independent-practice/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

• A worked example that is correct, with every step shown
• The target skill, in one line
• What learners already know, and their year group or level
• Mistakes you often see (optional)
• How many problems you want and how long learners have (optional)
• Real learner answers, if you have them (optional)

Helpful context (optional)

• Two or three real learner answers, to test the understanding check.
• The worksheet or textbook page the example came from.

Tools and access

• Claude, ChatGPT or Gemini with file support: They can read your example as text or a photo of a page. Check any maths or code answers yourself.

Functions and deliverables

• Worked-example practice sequence builder: Share a correct example, learner level and target skill. Get guided steps, practice problems, answer checks and a short reasoning review.
  • A staged sequence: a full model, problems with fading steps and problems to solve alone
  • Comparable problems with worked answers and a note on how hard each one is
  • A short understanding check that asks why, with a feedback line for each likely wrong answer
  • A rule for what to practise next after each kind of mistake
  • A summary of what was not checked and one next step
• Worked-example practice ladder builder: Turn any multi-step procedure into worked examples that fade into independent practice. Get a worked example sequence your students can follow.
  • Fully worked examples
  • Partly completed examples
  • Independent practice tasks
  • Self-explanation prompts
  • Guidance on pacing the fade
  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.
• Study understanding checker: Check your understanding after you study. Share your notes or a chapter and get questions or a worked practice problem, plus feedback on each answer.
  • Four to six numbered questions that ask you to apply, explain, connect, spot an error or predict
  • A step-by-step worked example, if you want to practise a method
  • A slightly harder practice problem for you to solve
  • Short feedback on each answer: what is right, where the reasoning went off and a hint
  • A summary of what is solid, where the gaps are and where to look in the source
  Source: Jacquard Labs.
• 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 taught a method and students nod, then cannot start the homework.
• You have one good worked example and need a full practice sheet from it.
• Students get right answers but cannot say why they work.
• You are setting cover work or homework and need staged practice with an answer key.

Limits to check before starting

• You have no worked example yet. Build the steps first with the Worked-example practice ladder builder.
• You only need a set of problems. Use the Practice problem set writer.
• You are planning how to fade help across a unit, not writing the problems. Use the Independent practice planner.
• The example is for an online course. Use the Online worked example builder.

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 your worked example, the skill, the level and the mistakes you see. Say how many problems you want.
• Read the stages from step 1 before the problems are used, and check that each stage takes away the steps the plan says. Then solve two of the AI's problems yourself and check them against its answers before you print anything.
• Run the understanding check with learners, then bring their answers back to choose the next practice.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/turn-a-worked-example-into-independent-practice 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.