Prompt Engineering Tutorial
Learn to write better prompts for ChatGPT, Claude and Gemini — a practical, beginner-friendly course in 20 interactive lessons, each with short Python examples you can run in your browser.
Learn prompt engineering from scratch: write better prompts for ChatGPT, Claude and Gemini with roles, examples, chain-of-thought and output formats.
👋 New to AI? You're in the right place.
Start with Lesson 1 — by the end you'll prompt any AI like a pro.
Continue where you left off
Lessons in this course
- What Is Prompt Engineering? — Why how you ask changes what AI gives you — and what this skill is worth
- How AI Models Read Your Prompt — Tokens, context windows, and why models predict the most likely reply
- Anatomy of a Great Prompt — The five ingredients: role, task, context, format, and constraints
- Context & Being Specific — Replace vague requests with the background and detail the model needs
- Role & Persona Prompting — 'Act as a…' — set expertise, audience, and tone for sharper answers
- Few-Shot Prompting with Examples — Show input→output examples so the model copies the pattern you want
- Chain-of-Thought Reasoning — Ask the model to think step by step on harder, multi-step problems
- Controlling the Output Format — Get JSON, tables, bullet lists or a set length — exactly as you need it
- Prompting AI to Write Code — Give language, version, the error and the goal — then read and test the result
- Iterating & Refining Prompts — Steer a near-miss to a great answer with precise follow-up prompts
- Avoiding Hallucinations & Fact-Checking — Why models make things up — and how to ask for sources and verify
- Reusable Prompt Templates & Cheat Sheet — Copy-paste templates and a one-page recap of every technique
- System Prompts & Setting Behavior — Use the system message to set persistent role, tone, rules and guardrails
- Structured Output: JSON & Schemas — Get reliable machine-readable output with schemas, JSON mode and validation
- Tool & Function Calling — Let the model call your functions and APIs in a call-execute-observe loop
- Retrieval-Augmented Generation (RAG) — Ground answers in your own documents with embeddings and retrieval
- Prompting AI Agents — Multi-step planning, the ReAct loop, tools and stopping conditions
- Multimodal Prompting (Images & Vision) — Prompt effectively with images for analysis, extraction and OCR
- Prompt Injection & Safety — Defend against jailbreaks and injection when prompts include untrusted text
- Evaluating & Testing Prompts — Build eval sets, grade with rubrics or an LLM judge, and prevent regressions
More for this course
- Best AI Tools for Learning to Code (and How to Use Them) — Which AI tools genuinely help a beginner learn programming faster, which ones quietly stop you learning, and how to use them so you still understand your own code.