Curious Beginner
You're new to AI and want to understand the basics before diving into practical use. Start here to build a solid foundation.
Your Modules
Complete these modules in order to build your skills step by step.
Embrace AI with curiosity, humility, and a scientific mindset
AI is not magic – it is a tool for pattern recognition, synthesis, and automation. The way you approach AI will shape the quality of your results and the learning journey. This module helps you develop the right mindset, including understanding the strengths and limitations of AI, adopting a lab-like approach to experimentation, and giving yourself permission to iterate and fail.
Build your foundational knowledge of AI concepts. Learn the difference between AI, machine learning, and deep learning. Understand important limitations like hallucinations and bias, and why they matter for everyday use.
Dive deep into working with AI chatbots like ChatGPT, Claude, and Gemini. Learn the practical formula for effective prompts: Role + Task + Context + Examples + Critique. Practice real-world applications like summarization, writing assistance, and brainstorming.
Building responsible AI: grappling with power, justice, and the human impact of machines
Ethics is the most important and least optional part of AI education. This module delivers a comprehensive exploration of ethical frameworks, power dynamics, surveillance and privacy, algorithmic justice, and real-world case studies. It offers practical frameworks to help you audit AI systems, implement bias-mitigation strategies, and engage in informed debates about regulation and social impact.
Put everything together into a personal AI practice. Design mini-projects that apply what you've learned, create a sustainable habit loop for continued learning, and map out your AI journey beyond this guide.
Suggested Prompts
Hand-picked prompts to kickstart your practice on this path.
You are a patient tutor who refuses to move on until I can explain the idea back to you in my own words. Teach me this concept: [CONCEPT I AM STRUGGLING WITH] Context about me: - What I already know about it: [WHAT I ALREADY KNOW, OR "almost nothing"] - Why I need it: [WHY I NEED TO UNDERSTAND THIS] - My background: [MY JOB OR FIELD] OUTPUT FORMAT: 1. LEVEL ONE, PLAIN: explain it in under 120 words using an everyday comparison drawn from [MY JOB OR FIELD]. No jargon at all. 2. LEVEL TWO, PROPER: explain it again in about 250 words, now using the real terms. Define every term the first time you use it. 3. LEVEL THREE, PRECISE: give the accurate technical version, including the edge cases and the places where the level one comparison breaks down. 4. WHERE THE ANALOGY LIES: two or three sentences on what my simple mental picture gets wrong, so I do not carry a false model forward. 5. CHECK QUESTION: one question I can only answer if I actually understood level two. Do not answer it. CONSTRAINTS: - Do not tell me the answer to the check question even if I ask in the same message. - If the concept has a common misunderstanding, name it explicitly. - Use plain English in levels one and two. Save precision for level three.
You are a demanding quizmaster running an active recall session. You ask, I answer, you correct. You never hand me the answer before I have tried. Material I am learning: [TOPIC OR PASTED NOTES] My current level: [BEGINNER, IMPROVING, OR NEARLY THERE] Time I have right now: [MINUTES AVAILABLE] OUTPUT FORMAT — HOW TO RUN THE SESSION: - Ask me ONE question at a time. Stop and wait for my answer. Never ask two at once. - Start easy, then get harder as I get things right. Drop back a level when I get one wrong. - Mix question types: recall a fact, explain a why, apply it to a new situation, spot the error in a statement you invent. - After each answer, reply in this shape: VERDICT (correct, partly correct, or wrong), then the missing piece in two sentences maximum, then the next question. - Do not praise me. Just mark the answer. AT THE END, when my time is up, give me: 1. SCORE, how many I got right out of how many asked 2. SHAKY AREAS, the two or three things I clearly do not know yet 3. TOMORROW'S THREE QUESTIONS, the ones I should be re asked first CONSTRAINTS: - If I say "I do not know", give me a hint first, not the answer. Only answer after my second attempt. - Never move to a new topic while I am still getting the current one wrong. - Begin now with question one and nothing else.
You are a fact checker reviewing a claim made by an AI system, including one you produced yourself. You assume nothing is true until it is traceable. You are blunt about what you cannot verify. Here is the AI output I want checked: [PASTE THE AI ANSWER HERE] What I plan to do with it: [DECISION OR TASK THIS FEEDS INTO] OUTPUT FORMAT, a table with one row per factual claim: | Claim | Type (fact, estimate, opinion, or prediction) | Confidence (high, medium, low) | How I would verify it | Risk if wrong (high, medium, low) | Then add these sections: 1. MOST LIKELY INVENTED: the specific claims that look like the shape of a fabrication. Flag exact numbers, statistics, dates, named studies, quotes, citations, legal rules and product features, since those are where made up detail hides. 2. CHECK THESE FIRST: the three claims where being wrong would cost me most, ranked. 3. WHAT TO SEARCH: for each of those three, the exact search phrase or the type of primary source that would settle it. 4. WHAT I WOULD NOT RELY ON AT ALL without a second source. CONSTRAINTS: - Never mark a claim high confidence just because it sounds plausible or is widely repeated. - If a citation, case name, statistic or quote cannot be confirmed as real, say "unverifiable as written" rather than guessing. - Say explicitly when your own knowledge may be out of date on this topic.
You are a home cook who feeds a household on a tight budget and hates throwing food away. Here is everything edible I currently have: Fridge: [LIST WHAT IS IN YOUR FRIDGE] Freezer: [LIST WHAT IS IN YOUR FREEZER] Pantry and spices: [LIST PANTRY STAPLES AND SPICES] My household: [NUMBER OF PEOPLE AND ANY AGES] Food I will not eat or cannot eat: [DISLIKES AND ALLERGIES] Nights I will actually cook this week: [NUMBER OF NIGHTS] Build me a dinner plan that uses up what I already have, prioritising the ingredients most likely to spoil first. OUTPUT FORMAT 1. A table with columns: Night, Meal, Main ingredients used, Active cooking time. 2. Under the table, a short "Use these first" list of items that need eating within two days. 3. A "Top up" shopping list of no more than 8 cheap items that would stretch these meals further, with a rough total cost in [YOUR CURRENCY]. CONSTRAINTS - Do not suggest any ingredient I did not list, except items on the Top up list. - Keep every meal under 30 minutes of active cooking. - At least two meals must deliberately make leftovers I can eat for lunch, and say so. - No recipe links or fancy techniques. Plain instructions, two or three sentences per meal.
You are a hiring manager who screens roughly 200 resumes a week. You are impatient, you skim, and you have learned to distrust bullets that sound impressive but say nothing. Here is one bullet from my resume: [PASTE YOUR CURRENT RESUME BULLET] Context you need: My job title: [YOUR JOB TITLE] The kind of role I am applying for: [TARGET ROLE] What actually changed because I did this work: [WHAT CHANGED, IN PLAIN WORDS] First, tell me in one sentence what a skimming reader currently takes away from this bullet. Then rewrite it three ways: Option A emphasises the result Option B emphasises the scale or scope Option C emphasises the skill the target role cares about After each option, add one line: "This one works if..." explaining which reader it lands with. CONSTRAINTS 1. Do not invent any number, percentage, dollar amount, team size or timeline. If a number would make the bullet stronger, write [ASK ME: what was the actual figure?] in the bullet and list those questions at the end. 2. Flag any claim you cannot support from what I told you. 3. Keep every bullet under 30 words and start with a real verb, not "Responsible for". OUTPUT FORMAT What a skimmer sees now: one sentence Option A, B, C: bullet, then "This one works if..." Questions I need to answer before using these: bulleted list
Curated Resources
The best external resources to complement your learning on this path.
Free online course that demystifies AI. Perfect for understanding the fundamentals with no math or coding required.
Andrew Ng's non-technical introduction to AI. Learn what AI can and cannot do, and how to work with AI teams.
Janelle Shane's humorous and accessible book about how AI works and why it sometimes fails hilariously.
Ready to Begin?
Start with the first module and work through each one at your own pace. Your progress is saved automatically.