Beginner · 5h 38m · 25 lessons
Prompt Engineering Basics
Learn to talk to AI models so they actually do what you want.
What you'll learn
- ✦Explain what a prompt is and how a language model turns it into a response
- ✦Write clear, specific prompts that cut down guesswork and made-up answers
- ✦Apply zero-shot, few-shot, and role-based prompting to a real task
- ✦Break a complex problem into steps using chain-of-thought and task decomposition
- ✦Spot and fix common prompt failures like vague, overloaded, or contradictory prompts
- ✦Build reusable prompt templates you can keep and improve over time
- ✦Reduce hallucinations by grounding prompts in real sources and asking for a self-check
- ✦Use prompts safely inside an application: evaluate them, version them, and defend against prompt injection
Part of these career paths
- AI-Assisted Developer path · course 1 of 5
Certification projects
Build 4 projects to earn your certificate
Hands-on work that proves you can apply what you learned — part of the certificate requirements.
Syllabus
Module 1 · 56m
What is a prompt? Free
What you'll be able to do
- Can explain what a prompt is and how a model turns it into a response.
- Can explain what a token is and why it limits how much a prompt can hold.
- Can predict why two similarly worded prompts give different answers.
- Can name the four parts of a well-built prompt: instruction, context, input, output format.
Module 2 · 1h 10m
Core techniques Pro
What you'll be able to do
- Can rewrite a vague prompt into a specific one with a clear audience, length and goal.
- Can add the context a model needs — who you are, what it's for, who reads it.
- Can choose zero-shot or few-shot examples to teach a model an exact pattern.
- Can assign a role and specify an output format to shape a model's answer.
Module 3 · 1h 4m
Advanced patterns Pro
What you'll be able to do
- Can use chain-of-thought and task decomposition to solve a multi-step problem.
- Can iterate on a prompt, one constraint at a time, instead of rewriting from scratch.
- Can decide whether an instruction belongs in a system prompt or a user prompt.
- Can add a simple guardrail so a response stays inside safe, relevant boundaries.
Module 4 · 1h 13m
Prompting in practice Pro
What you'll be able to do
- Can write prompts that explain, write, debug and review code with AI.
- Can write prompts for drafts, rewrites, summaries and tone changes, and for pulling insights out of real data.
- Can spot and fix a vague, overloaded or contradictory prompt.
- Can save a working prompt as a reusable template.
Module 5 · 37m
Prompting for reliability Pro
What you'll be able to do
- Can prompt in ways that make made-up answers (hallucinations) less likely.
- Can ground a prompt in real source text instead of the model's memory.
- Can ask a model to review and fix its own first answer.
Module 6 · 38m
Prompts at scale Pro
What you'll be able to do
- Can explain what changes when a prompt is built into an application by code.
- Can evaluate and version a prompt like a piece of code before shipping a change.
- Can recognise a prompt injection attempt and name a basic defence against it.
More AI courses
✦ Pro
AI for Developers
See how LLMs really work, then use AI in your daily dev work without trusting it blindly.
✦ ProChatGPT & Claude for Coding
Use ChatGPT and Claude to write, debug and understand code, and check every word they say.
✦ ProBuild with the Claude API
Go from a blank file to a working AI feature, one Claude API call at a time.