Teaching has always had two distinct workloads: the human one (being in the room with students) and the paper one (planning, marking, designing assessments). AI cannot do the first — but it can give you back several hours a week of the second, if you prompt it like a professional. This tutorial shows you how to turn AI into a tireless assistant that drafts, never decides.
Most teachers do not need AI to "do their job". They need AI to take the first 70% of a task — the draft lesson plan, the bank of practice questions, the first version of a rubric — so they can spend their limited preparation time on the 30% that requires professional judgement. The danger is the opposite: copying an AI-generated lesson straight into the classroom and discovering at 9:15 a.m. that it does not actually match your students, your syllabus, or your school's policy.
The prompts in this tutorial are designed to keep you firmly in the editor's seat. AI drafts; you decide. With practice, you will find a lesson plan that used to take an hour now takes fifteen minutes — and the fifteen minutes are spent on the parts that matter.
A great teacher prompt does three things: it tells AI exactly which curriculum and level you are teaching, it forces output into a structured lesson-plan template, and it builds in differentiation so the plan serves stronger and weaker students in the same room.
Most school lesson plans follow a recognisable rhythm — a hook to grab attention, an explicit learning objective, direct instruction, guided practice, independent practice, and a check for understanding at the end. If your prompt names that structure, AI fills each block far more usefully than if you simply ask for "a lesson plan".
Weak prompt
Write a lesson plan on photosynthesis.
You get one page of generic prose: "Begin by introducing the concept of photosynthesis. Then discuss the chloroplast." It does not say how long each part should take, what the students actually do, what to write on the board, what the exit question is, or how to support a struggling reader in the same class. You will end up rewriting all of it.
Strong prompt — lesson plan
Act as an experienced Year 8 science teacher.
Plan a single 50-minute lesson on
"Photosynthesis: inputs, outputs, and why it matters"
for a mixed-ability class of 28 students.
Use this exact structure with time allocations:
1. Hook (5 min) — a curiosity question or short demo
2. Learning objective (2 min) — written on the board,
one sentence, student-friendly language
3. Direct instruction (15 min) — key concepts, with
one analogy and one diagram I should draw
4. Guided practice (10 min) — paired task, with the
exact instruction I read out
5. Independent practice (10 min) — short worksheet,
include 3 questions ranging easy → challenging
6. Exit ticket (8 min) — one written question that
tells me who has understood
Also include:
- One differentiation strategy for two stronger students
- One scaffold for two students who struggle with reading
- A list of materials I need to prepare
This produces a plan you can almost teach from directly. You will still tweak the analogy or the hook, but the skeleton is done — and the differentiation and exit ticket are no longer afterthoughts.
Generate a 20-question end-of-unit quiz on [topic] for Year [X]. Mix of formats: 10 multiple choice, 5 short answer, 3 problem-solving, 2 extended response. Provide a separate mark scheme. Mark each question's Bloom level so I can see the balance.
Create a 4-level marking rubric for a [task type] in [subject]. Levels: Emerging, Developing, Secure, Mastery. For each level, give one observable indicator per criterion (3 criteria: content accuracy, structure and clarity, use of evidence). Use language students can read.Tip: Build a "teacher prompt library" file — one lesson-plan template, one quiz template, one rubric template, one parent-email template. Each starts as a strong prompt with placeholders for the topic and year group. After a term, you will be filling in three blanks instead of writing the prompt from scratch each time.
Pick a lesson you will teach next week. Write a single prompt that includes year group, topic, lesson length, the six-block structure, two differentiation requirements, and an exit ticket. Run it. Compare AI's draft to the lesson you would have planned yourself — what did each version miss?
Generate a 20-question end-of-unit quiz on your current topic. Specify the question-type mix, Bloom-level mix, and ask for a separate mark scheme. Read through every question carefully — flag any that feel ambiguous, double-barrelled, or culturally narrow, and prompt AI to rewrite just those.
Build a 4-level rubric for an upcoming essay or project. Use the prompt from Step 3 above. Then ask AI: "Now rewrite the 'Emerging' and 'Developing' descriptors in language a 13-year-old would understand without a dictionary." Student-readable rubrics improve self-assessment dramatically.
Sign in to join the discussion and post comments.
Sign inPrompt Engineering Projects & Real-World Applications
Twelve hands-on projects that turn prompt engineering theory into a portfolio. Build chatbots, content generators, RAG systems, and more.
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 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.
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.
Prompt Engineering for Specific AI Tools
Tool-by-tool mastery — deep dives into ChatGPT, Claude, Gemini, GitHub Copilot, Midjourney, Stable Diffusion, and more. Learn the exact prompting techniques each platform rewards.
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.