Module 02 — Core Skill

The Art of
Prompting

The single most valuable AI skill isn't coding — it's knowing how to direct AI precisely. This module teaches you to write prompts that get extraordinary results, and to spot when AI is misleading you.

⚠️
AI risks — what you need to know.
This module includes a dedicated lesson on AI dangers — hallucination, deepfakes, manipulation and how to protect yourself. Understanding risks is part of being genuinely AI-literate.
5
Lessons
300
XP available
~60
Minutes
1
Badge to earn
LESSON_TRACK

Your Learning Path

Module progress 0 of 5 lessons complete
1
Video
2
Anatomy
3
Lab
4
Safety
5
Library
→ Start with Lesson 1 below
🎬
1. What Makes a Great Prompt?
Watch: the difference between weak and powerful prompts — with real examples
+50 XP
01
Prompt Engineering — how to get the best from AI
OpenAI / community guide · ~8 min · Core skill lesson

Pay attention to the before/after examples — the gap between a weak prompt and a strong one is enormous. You'll replicate that gap yourself in Lesson 3.

// Watch for these 3 things in the video
→ How adding context changes the output completely
→ Why telling AI who it is matters
→ How specifying format saves you time editing
Rate this lesson:
saved ✓
🔍
2. Prompt Anatomy — Dissecting What Works
Click each colour-coded part of a prompt to understand what it does
+50 XP
02

Every great prompt has distinct parts working together. Click each highlighted section below to learn what it does and why it matters. Then try building your own.

Role
Context
Task
Format
Constraint
You are an expert football analyst helping a 14-year-old who is new to tactics. Explain what a high press is and why teams use it. Use a real Premier League example and keep it under 150 words. Avoid jargon — explain any technical terms you use.
↑ Click any highlighted section above to see what it does
⚡ BUILD A PROMPT — click one chip from each row
Prompt strength 0 / 5 parts selected
🟣 ROLE — who should the AI be?
🟢 CONTEXT — what's the situation?
🟡 TASK — what do you want?
🔵 FORMAT — how should it respond?
🔴 CONSTRAINT — what should it avoid?
Rate this lesson:
saved ✓
🧪
3. Prompt Puzzles — Fix the Broken Prompts
You're given a bad prompt. Rewrite it to get a better result. 4 challenges
+70 XP
03

These are real prompts people type into AI — and they're all weak. Your job is to rewrite each one so it would get a dramatically better response. There's no single right answer — just better and worse.

PUZZLE 01
The homework prompt
❌ WEAK PROMPT
"Help me with my essay"

Why is this bad? The AI has no idea what subject, what level, what the essay is about, what kind of help you want, or how long it should be. It'll give you something generic and useless.

PUZZLE 02
The revision prompt
❌ WEAK PROMPT
"Explain photosynthesis"

This will get you a Wikipedia-level answer that's too long, too technical, and impossible to revise from. How could you make this perfect for a Year 9 biology test?

PUZZLE 03
The creative prompt
❌ WEAK PROMPT
"Write me a story"

You'll get something generic and forgettable. What if you want something set in a specific world, with a specific tone, that's the right length to actually read?

PUZZLE 04 — ADVANCED
The chain-of-thought challenge
❌ WEAK PROMPT
"Is it better to revise alone or in a group?"

This gets you an opinion. But what if you want the AI to actually reason through it — weigh the evidence, consider your specific situation, and reach a conclusion? That requires chain-of-thought prompting.

Rate this lesson:
saved ✓
⚠️
4. When AI Goes Wrong — Risks You Need to Know
Hallucination, deepfakes, manipulation — how to protect yourself
+60 XP
04

AI can be genuinely dangerous when misunderstood. Here are the four biggest risks — and what you can do about each one.

🤥
Hallucination — AI that confidently lies
Click to expand

AI language models don't "know" things the way you do. They predict what words come next based on patterns — which means they can produce completely made-up facts that sound absolutely convincing. This is called hallucination.

Real example: a lawyer in the US used ChatGPT to write a legal brief. It cited six court cases to support its argument. All six cases were completely fabricated. The lawyer submitted it to court without checking. He faced serious professional consequences.

❌ Dangerous use
"What are three scientific studies that prove video games improve reaction time? Include the authors and years."

→ AI will generate convincing fake citations. Never cite AI-provided sources without verifying them.
✓ Safe use
"Explain the general research findings on video games and reaction time. I'll find the actual studies myself."

→ Use AI for understanding, not for citations. Always verify specific facts.
🎭
Deepfakes — AI that puts words in people's mouths
Click to expand

AI can now generate realistic video and audio of real people saying things they never said. You can clone someone's voice from 3 seconds of audio. You can create video of someone's face saying anything. This technology is already being used to spread misinformation, create fake celebrity content, and scam people.

The red flags to look for: unusual blinking patterns, slightly off lip sync, unnatural skin texture around the edges of the face, background that doesn't quite match. But these are getting harder to spot every month.

❌ Warning signs
Video of a famous person saying something shocking. Audio message from someone you know asking for money urgently. Images that look slightly "too perfect" or have warped backgrounds.
✓ How to protect yourself
Check the original source. Search for the same story on multiple news sites. For audio from someone you know — call them back on a number you already have. Never send money based on an audio or video message alone.
🎯
AI-powered manipulation — personalised persuasion
Click to expand

This is the one most people don't think about. AI can analyse your social media, your interests, your fears, and your beliefs — then generate content specifically designed to push your buttons. Political ads, scam emails, fake news — all increasingly personalised to you specifically.

The reason this is so effective is that it doesn't look like advertising. It looks like content you'd naturally agree with. It confirms what you already believe, which makes it very hard to question.

❌ How to spot it
Content that makes you feel very strongly — angry, scared, outraged — about something. Posts that seem designed to confirm exactly what you already believe. News that you only see in one place and can't verify elsewhere.
✓ The defence
Before sharing anything that made you feel strongly emotional — pause. Search for it. Does a reputable news source cover it? Could this be designed to make you react? The pause is the most powerful tool against manipulation.
🧠
Overdependence — losing your own thinking
Click to expand

This is the quietest risk — and possibly the most important one for someone your age. If you always ask AI to write your essays, solve your problems, and make your decisions, your own ability to do those things will get weaker. Just like a muscle you never use.

The goal of this course is the opposite of overdependence. We want you to be someone who uses AI as a tool that amplifies your own thinking — not replaces it. The people who will do best with AI are the ones who can think critically, evaluate outputs, and direct the AI rather than just accept what it says.

❌ Overdependence pattern
"Write my essay for me." → Submit it → Never engage with the topic → No learning happens → Next assignment, repeat. Your writing and thinking skills deteriorate.
✓ The amplifier pattern
"I've written a draft. Give me feedback on my argument structure." → Read the feedback → Decide what to change → Rewrite yourself. AI improves your work. You improve too.
// The one rule that covers everything

If something made by AI made you feel a strong emotion — shock, fear, anger, excitement — pause before acting on it. That emotion is the mechanism. The pause is the defence.

Rate this lesson:
saved ✓
📚
5. Project — Build Your Personal Prompt Library
Create 6 tested prompts across different areas of your life. Keep these — they're yours
+70 XP
05

A prompt library is a personal collection of prompts that work — tested, refined, and ready to use. Professional AI users all have one. Build yours now across 6 categories. Use everything you've learned in this module.

0 of 6 prompts written
Rate this lesson:
saved ✓
0
XP earned in Module 2
🎯

Prompt Master badge unlocked. Module 3 — AI Tools in the Real World — is now unlocked.

// Module 3 preview
→ Guided tours of Claude, Perplexity, Midjourney, Copilot
→ Match the right AI tool to the right task
→ Use AI to tackle a real school assignment
Coming next...
Q1 Which lesson was most useful — and why?
Q2 Was anything too easy, confusing, or skippable?
Q3 Overall difficulty?
Q4 What would make Module 3 even better?
▶ Module 2 feedback report — share with a parent or guardian
🤖 AI Tutor