Who it's for
For anyone who uses AI chat and wants better results, with no coding needed. You need a chat window on Claude, ChatGPT or Gemini and one task you repeat. Claude Code is optional, and two exercises use it.
Lessons
- 1Prompt engineering basics: how to write prompts that workPrompt engineering basics in one lesson: be specific, add context, show examples, ask for a format and iterate. Drawn from Anthropic, OpenAI and Google guides.
- 2How to write a system prompt, with a worked exampleA system prompt sets standing rules for a whole AI conversation. Learn to write one in four parts, where each vendor puts it and what it cannot do.
- 3What is a context window? What fills it and what to do when it is fullA context window is the text a model can use at one time. See what fills it, how big current windows are, what happens when it is full and how to work in it.
- 4What is an AI agent? How it differs from a chatbot and a workflowAn AI agent is a model that picks its own next step and calls tools in a loop. See how it differs from a chatbot and a fixed workflow, and when to build one.
Frequently asked questions
Is this prompt engineering course free?
Yes. Every lesson in Mindket's Learn section is free to read, and the exercises need only a chat window.
What do I need to start?
An AI chat such as Claude, ChatGPT or Gemini, and one task you do more than once. Claude Code is optional, and only a few exercises in the context window and agent lessons use it.
How long does the course take?
Each lesson takes about six or seven minutes to read, plus the time you spend on its exercise.
Where does the course content come from?
From the prompting guides, API pages and engineering articles of Anthropic, OpenAI and Google, plus Claude Code's docs. Each lesson lists its sources, and none of it is hands-on testing.
What comes after this course?
Which AI tool to use is next. It compares the apps for images, video, voice, music, research and AI agents, and the Learn hub lists the other courses.