Free prompt engineering course
Learn to write prompts that work reliably, then test them like an engineer: clear instructions, examples, structured output, chains, evals and defenses against prompt injection.
Create a free account Try the first lesson
What you'll be able to do
- Turn a vague request into a prompt with a task, context, constraints and an output format
- Decide what belongs in a system prompt, and write one for an app
- Use examples (few-shot prompting) to settle the cases your instructions leave open
- Get JSON your code can rely on, by describing it with a schema and checking what comes back
- Split a big task into a chain of small model calls, with checks between the steps
- Spot prompt injection, and apply layered defenses in code
- Use an eval to compare two prompts before you ship a change
Who it's for
For anyone building with language models who wants results they can count on, rather than a list of magic phrases. You'll write a little Python, so you can test a prompt on many inputs instead of one.
Before you start
Some lessons here build on earlier ones in the academy. The placement test can mark off what you already know, and you can open any of them first:
New to Python? Start with the free Python for AI course.
The 14 lessons
One is free with no account, and a free account opens the rest.
- What an LLM actually does FreeNext-token prediction, and why that produces useful behavior.
- Tokens and the context windowHow text becomes tokens, and what fits in one request.
- Prompt fundamentalsClear instructions, context and constraints: the 80% of prompting.
- System prompts and rolesSet behavior once, separately from the conversation.
- Examples in promptsShow the model what good looks like (few-shot prompting).
- Structured outputGet reliable JSON back that your code can use.
- Prompt chainingBreak big tasks into a pipeline of smaller model calls.
- Choosing a modelTrade capability, speed and cost across model families.
- Reasoning models and effortWhen models think before answering, and how to control it.
- Conversations and memoryAPIs are stateless: how chat history and memory really work.
- Tool useLet the model call your functions (function calling).
- Prompt injection and securityHow untrusted text hijacks models, and how to limit the damage.
- EvalsMeasure output quality with test sets instead of vibes.
- LLM-as-judgeGrade open-ended output with rubrics and a second model.
When you finish
Finish every lesson, or show you know it in the placement test, and you earn a certificate of completion, "Prompt engineering course", with its own link you can share or add to LinkedIn.
Questions
- Is it really free?
- Yes. There's nothing to pay, here or anywhere in the academy. A free account saves your progress and issues your certificate.
- Do I need to install anything?
- No. The Python in these lessons runs in your browser.
- How long does it take?
- About 8 hours in all, at your own pace. Your progress stays where you left it.
- What does the certificate show?
- That your account recorded every lesson as finished or known. It's a certificate of completion from Index Ai Academy, not an accredited qualification.
Start the course
A free account saves your progress across devices and issues your certificate when you finish.