Active recall — pulling information out of your head — is the single most powerful study technique we know of. AI gives you an unlimited supply of questions tailored to your exact syllabus, difficulty level, and weak spots. The catch is that the default prompt produces lazy, predictable questions. This tutorial shows you how to ask for the kind of test that actually stretches you.
Most students re-read their notes and call it revision. Decades of research suggest this is one of the worst uses of study time. What works is the opposite: closing the book and forcing yourself to retrieve the information from memory. Every retrieval strengthens the memory. The problem has always been finding enough quality questions to test yourself with — past papers run out, textbook exercises feel repetitive, and writing your own questions is impossible because you do not yet know what you do not know.
AI solves that bottleneck. With a single thoughtful prompt, you can produce twenty fresh questions of escalating difficulty on any chapter you choose. But generic prompts produce generic questions — the kind that test recall of a definition and nothing else. This tutorial gives you the prompt patterns that produce the harder, deeper questions that real exams ask.
Good questions come in layers. Educators call this Bloom's taxonomy — a ladder of thinking skills from simple recall at the bottom up to creation and evaluation at the top. A well-designed mock test mixes questions from across the ladder. AI, by default, sits stubbornly at the bottom two rungs. You have to explicitly ask it to climb.
Imagine you are studying photosynthesis. A bottom-rung question is "What is the chemical equation for photosynthesis?" — you either remember it or you do not. A top-rung question is "A plant placed in red light grows faster than one in green light. Explain why, and predict what would happen under pure blue light." That second question requires you to understand the chlorophyll absorption spectrum, apply it to a new scenario, and reason about an outcome. Both questions are valid, but they train different muscles.
The mental model is simple: when you prompt AI for questions, tell it exactly which rungs you want and in what mix. Three "remember" questions, three "apply", two "analyse", and one "evaluate" — for example. The result is a mini mock test that feels like a real exam, not a flashcard deck.
Here is the kind of prompt almost every student starts with — and the kind of result it produces.
Weak prompt
Give me practice questions on the French Revolution.
AI will produce ten questions, almost all of them at the "remember" level: "When did the French Revolution begin?", "Who was Louis XVI?", "What was the Bastille?" Useful for a quiz night, useless for an actual history exam, which will test causation, comparison, and argument.
Strong prompt
Act as an experienced history examiner who writes
A-Level question papers.
Generate a 10-question practice paper on
"Causes and consequences of the French Revolution
(1789–1799)" for a Year 12 student.
Mix of question types:
- 2 short-answer (factual recall, 2 marks each)
- 4 medium-answer (explain or compare, 6 marks each)
- 3 source-analysis (interpret a short quoted source,
8 marks each — invent realistic sources if needed)
- 1 essay question (25 marks, 40-minute response)
Constraints:
- Question difficulty should escalate from Q1 to Q10
- Use the actual command words used in real exams
(describe, explain, assess, to what extent)
- After the paper, list the mark scheme for each
question but DO NOT give the model answers yet —
I want to attempt the paper first.
This prompt gives AI a role, a syllabus, a question mix, a difficulty curve, and a clear two-step workflow (paper first, answers later). The output will look and feel like a real exam paper — because you have described one.
Tip: Keep a "missed questions" log. Every time AI marks a question wrong, paste it into a separate note. After a week, ask AI: "Here are the questions I keep getting wrong. What pattern do you see? What concept am I weak on?" The diagnosis is often more valuable than the questions themselves.
Pick one chapter from a subject you are currently studying. Prompt AI for a 10-question mini-paper using a specific Bloom mix (e.g. 3 remember, 4 apply, 2 analyse, 1 evaluate). Attempt the paper under timed conditions before asking for the mark scheme. Notice how the harder questions reveal gaps the textbook re-reading missed.
Ask AI to generate a question in the style of a specific past exam: "Write one essay question on [topic] in the style of the GATE Computer Science 2022 paper. Match the typical wording, mark allocation, and expected answer length." Compare the AI question to a real past paper — how close did it get?
Try the "diagnose me" prompt: after completing five practice questions on a topic, paste your wrong answers and ask: "Look at these wrong answers together. What underlying misconception or knowledge gap is causing me to lose marks? Suggest the one topic I should re-study before continuing." This converts your mistakes into a study plan.
Sign in to join the discussion and post comments.
Sign inPrompt Engineering for Developers
Use AI as your coding co-pilot. 18 tutorials on writing prompts to generate clean code, debug faster, write tests, build APIs, and ship better software.
Prompt Engineering for Data Science & Analytics
Supercharge your data workflows with AI. 15 practical tutorials on using prompt engineering for data cleaning, EDA, machine learning, SQL, visualisation, and more.
Prompt Engineering for Image Generation
Turn words into stunning visuals. Master AI image generation tools like Midjourney, DALL·E 3, and Stable Diffusion with 18 focused tutorials — from first prompt to full brand identity.
Advanced Prompt Engineering Techniques
Master the powerful techniques AI experts use every day. Chain-of-thought, RAG, agents, function calling, prompt evaluation, and much more — 20 deep-dive tutorials.
Prompt Engineering for Business & Productivity
Use AI to work smarter — automate tasks, make better decisions, and communicate professionally. 12 practical business prompt tutorials for professionals.
Prompt Engineering for Content & Copywriting
Write blogs, ads, emails, and social media content ten times faster with AI. 13 practical tutorials on prompt engineering for content creators and copywriters.