Education & Curriculum5.0 · 0 ratings

Worked-Example To Faded-Practice Sequence

Builds a cognitive-load-optimized progression from fully worked examples to independent practice for procedural skills.

Role-BasedStep-by-StepFew-Shot

Prompt

ROLE: You are a cognitive-load theorist designing instruction for procedural skills using the worked-example and completion-problem effects.

CONTEXT: Skill or procedure: [SKILL]. Subject/level: [LEVEL]. Typical learner errors: [ERRORS]. Prerequisite skills assumed: [PREREQS]. Practice time: [MINUTES].

TASK: Build a faded-guidance sequence.
1. Present ONE fully worked example with every step shown and the reasoning narrated (especially at decision points).
2. Create a 'completion problem' where the first steps are done and the learner finishes the rest.
3. Create a 'completion problem' with more steps removed (fading guidance).
4. Provide a fully independent problem at the same difficulty.
5. Provide one transfer problem in a new surface context.
6. For each step in the worked example, flag where [ERRORS] typically occur and add a guardrail prompt.

OUTPUT FORMAT: Five labeled stages (Worked → Completion-1 → Completion-2 → Independent → Transfer), with answer keys. Include an 'error hotspots' note tied to the worked example.

CONSTRAINTS: Reduce extraneous load — no irrelevant decoration or split-attention. Fade guidance gradually; don't jump from full support to nothing. Keep difficulty constant across stages 1-4 (only support changes); only stage 5 changes context.

How to use this prompt

  1. 1

    Copy the prompt above and paste it into ChatGPT, Claude, or Gemini — or open it in the visual Studio to edit each part on a canvas and run it with your own key.

  2. 2

    Replace any bracketed placeholders with your specifics. The more concrete your context and constraints, the sharper the result — see the 5-part prompt structure.

  3. 3

    Run it, then refine. Ask the model to critique and improve its own answer with self-critique prompting.

Techniques in this prompt

Role-Based

Assigns the model an expert persona so it adopts the right vocabulary, depth, and standards for the task.

Learn this technique
Step-by-Step

Forces explicit intermediate reasoning instead of jumping to a conclusion, which improves accuracy on hard tasks.

Learn this technique
Few-Shot

Includes worked examples so the model matches your format and quality by pattern, not description.

Learn this technique

Recommended models

claudegpt-4ogemini

Build on this prompt

Open it in the visual Studio to wire it into a full workflow with your own API key — or learn the craft behind prompts like this.

More in Education & Curriculum