This module expands on how AI can support learners, the ethical considerations involved, and how coaches can help learners use AI in a thoughtful and effective way. The goal is not to replace learning, but to enhance it.
Recognize that AI can act as an on-demand explainer, idea generator, and debugging assistant.
Understand that AI is fallible and sometimes confidently wrong.
Identify when AI can speed up learning—and when it may hinder deeper understanding.
Teach learners to ask clear, specific questions. (e.g., “Why is my loop running indefinitely?”)
Encourage learners to assess and understand the answer instead of accepting it immediately.
Show learners how to refine prompts, compare multiple responses, and ask follow-up questions.
Reinforce that AI is a tool for learning, not a substitute for understanding the underlying concepts.
Avoid over-reliance on AI.
Highlight the importance of verifying information to avoid misinformation.
Discuss bias in AI models and data privacy.
Discuss data biases in AI training and how this can influence output and suggestions.
Remind learners not to share personal, sensitive, or confidential information.
Encourage responsible and critical use.
Use AI to debug, brainstorm, and explore new concepts.
Teach learners to use AI-generated solutions as hints or starting points—not final answers.
Remind learners that AI should be used for problem-solving and not for replacing critical thinking.
AI can assist learners by providing explanations, suggesting solutions, and offering alternative approaches. However, it is not always accurate and should complement human guidance.
Ask Good Questions: Encourage specificity and clarity.
Verify Responses: Cross-check AI outputs.
Learn from AI: Understand the reasoning behind suggestions.
Context engineering is about giving the AI the right background, constraints, and example so it can produce useful, relevant responses. A well-crafted prompt makes the difference between a vague answer and a practical, instructive reply.
Key principles
Provide context: Tell the AI what the problem is, show the relevant code or data, and explain what you expect.
Bad: “Why is my code failing?”
Better: “Here’s my loop (paste code). I expect it to stop after 10 iterations but it runs indefinitely—what might be causing that?”
Be explicit about the desired format: Ask for step-by-step reasoning, short explanations, or code snippets as needed. “Explain the bug in two short bullets and give a one-line fix.”
Set constraints and assumptions: Limit scope to make results practical (language, libraries, complexity). “Suggest solutions that don’t use external libraries and will work in Python 3.10.”
Show an example or expected output: If you want a specific style or level, give a sample. “Write the explanation at a beginner level and include a short analogy.”
Use iterative prompting: Start with a broad prompt, then refine with follow-ups. Ask for clarifications, alternative approaches, or simplified versions. “Can you show a simpler example?” → “Now translate that into a short exercise for a beginner.”
Ask the AI to critique its own answer: Request limitations, edge cases, or tests to verify suggestions. “List three tests I can run to check this fix.”
Short examples
Debugging prompt (strong): “I have this Python loop (paste). It should stop after 10 iterations but it doesn’t. Explain the likely cause in two bullets and provide a corrected loop with a brief explanation of the fix.”
Explanation prompt (strong): “Explain how a function works to a beginner using a cooking analogy, then give one tiny code example they can run in under 30 seconds.”
Refinement prompt (follow-up): “Your example is good — can you simplify it one level further and include a one-line test the learner can copy-paste?”
Encourage learners to treat prompts like small experiments — change one thing at a time and compare outputs.
Teach them to include minimal, relevant context (not huge dumps) and to point the AI to what matters.
Remind them to critically evaluate AI suggestions and always verify results with tests or trusted documentation.
Context engineering turns AI from a black box into a more reliable learning partner, and it’s a skill learners can practice and improve, just like debugging or writing clear code.
Avoid over-reliance on AI for answers.
Recognize potential biases in AI outputs.
Remind learners not to input sensitive information.
Debugging: AI can suggest potential causes, but learners should test and verify, and make sure they understand the answer.
Brainstorming: AI is great for generating ideas for projects or solutions.
Exploring New Topics: AI can introduce concepts in simple terms and provide examples or practice questions.
Skill Building: Learners strengthen reasoning by evaluating AI suggestions and adapting them.
Again, it's important that learners, test and understand fully any AI output.
1. What is a key benefit of using AI in learning? A. It replaces the need for human coaching B. It provides instant explanations and alternative perspectives C. It guarantees correct answers every time D. It removes the need to practice problem-solving
2. Effective use of AI in learning requires learners to: A. Accept the first answer given B. Provide sensitive information for better accuracy C. Ask clear, specific questions and verify responses D. Use AI to complete tasks as quickly as possible
3. Ethical AI use includes: A. Relying fully on AI for all problem-solving B. Ignoring biases because AI is always neutral C. Using AI responsibly, transparently, and without sharing sensitive data D. Avoiding human judgment
4. How can AI support problem-solving without replacing critical thinking? A. By giving learners the full solution immediately B. By offering suggestions that learners analyse and test C. By preventing learners from making mistakes D. By removing the need to understand the process
Scenario: A learner uses AI to fix every coding error but doesn’t understand why the fixes work. They say, “AI makes it so much faster—I don’t think I need to learn the details.”
Task: Write 3–4 sentences explaining how you would:
Encourage deeper understanding
Reinforce the importance of learning the underlying concepts
Help them use AI alongside their own reasoning rather than instead of it
Scenario: Your learner wants AI to help them understand why their Python loop isn’t stopping. They write the following prompt:
“My code isn’t working. What’s wrong?”
As a coach, your goal is to help them improve this prompt using context engineering principles.
Task: Rewrite the prompt to make it clearer, more specific, and more useful for learning. Your improved prompt should include:
The relevant code
What the learner expected to happen
What actually happened
The type of explanation they want (e.g., beginner-friendly, step-by-step)