Sequence a complex technical concept from prerequisite knowledge and mental models through worked examples, guided practice, fading, independent application, and transfer.
This prompt has variables that can be replaced with your own information. Copy and use it with your preferred LLM, or try it out in the LearnerBox Prompt Playground.
Act as an experienced technical educator and cognitive apprenticeship instructional designer.
Create a scaffolding progression for the complex concept below.
Learner level and discipline:
{{learner_context}}
Technical concept:
{{technical_concept}}
Target performance:
{{target_performance}}
Known prerequisites and misconceptions:
{{prerequisites_misconceptions}}
Available examples, tools, and resources:
{{resources}}
Time and delivery context:
{{delivery_context}}
Design requirements:
1. Decompose the target performance into component knowledge, skills, decisions, and representations.
2. Identify prerequisite concepts and threshold concepts.
3. Map likely misconceptions, fragile knowledge, and cognitive overload points.
4. Create a progression through:
- activation of prior knowledge;
- conceptual model;
- terminology and notation;
- simple example;
- worked example;
- annotated example;
- completion problem;
- guided practice;
- varied practice;
- independent performance;
- troubleshooting;
- transfer; and
- reflection.
5. Explain what scaffold is provided at each stage and why.
6. Include multiple representations such as diagrams, equations, verbal explanation, code, tables, physical models, or simulations where appropriate.
7. Use contrasting cases to clarify boundaries and misconceptions.
8. Create checks for understanding before moving forward.
9. Define scaffold-fading criteria based on learner evidence.
10. Include deliberate practice and retrieval opportunities.
11. Include error diagnosis and debugging or troubleshooting routines.
12. Identify where expert modeling, think-alouds, coaching, or peer explanation are useful.
13. Preserve technical accuracy while reducing unnecessary complexity.
14. Do not invent formulas, standards, software behavior, safety rules, or technical facts.
15. Flag content requiring subject-matter, safety, regulatory, or technical validation.
Present the result as:
{{output_format}}
Include:
- performance decomposition;
- prerequisite map;
- misconception map;
- scaffold sequence;
- example progression;
- representation plan;
- checks for understanding;
- scaffold-fading criteria;
- independent and transfer tasks;
- troubleshooting routine;
- practice schedule; and
- validation questions.Replace each variable shown in double curly brackets with accurate information from your own professional context.
{{learner_context}}
Example: Example: New data analysts learning regression diagnostics
Identify learner background and technical field.
{{technical_concept}}
Example: Describe the concept, process, method, model, or system to be learned.
Be specific about the concept boundaries.
{{target_performance}}
Example: Describe what learners should independently explain, calculate, build, diagnose, or decide.
The progression should end in observable independent performance.
{{prerequisites_misconceptions}}
Example: List assumed knowledge, common errors, confusing representations, and threshold concepts.
This helps prevent gaps and cognitive overload.
{{resources}}
Example: List software, datasets, equipment, diagrams, worked examples, labs, and simulations.
Only available resources should be assumed.
{{delivery_context}}
Example: Example: Four 90-minute workshops with online practice
State duration, mode, class size, and practice opportunities.
{{output_format}}
Choose the format required for course design or teaching.
A technically grounded learning progression containing performance decomposition, prerequisites, misconceptions, staged scaffolds, varied representations, worked examples, checks, fading criteria, independent application, troubleshooting, and transfer.
These characteristics describe the type of thinking, customization, and output structure involved in using this prompt effectively.
This breakdown explains how the prompt’s major components work together to guide the AI toward a useful, reliable, and well-structured response.
Positions the AI as a technical educator and cognitive-apprenticeship designer.
Defines learners, concept, target performance, prerequisites, resources, and delivery context.
Requires a staged scaffold from mental model to independent transfer.
Prevents invented technical facts, standards, formulas, software behavior, and safety rules.
Requires decomposition, maps, progression, representations, checks, fading, troubleshooting, and practice.
Learners, concept, performance, prerequisites, resources, delivery, and output format.
AI-generated responses can contain errors, omissions, unsupported assumptions, outdated information, or recommendations that do not reflect your jurisdiction or professional context.
Verify calculations, evidence, regulations, standards, policies, and professional recommendations before relying on the result. The qualified professional remains responsible for the final decision.
Return to the specialization page to explore additional professional workflows and prompt templates.
Customize the template for your professional context or open it directly in the Prompt Playground for guided AI practice.