Mindket
BeginnerFree

AI basics course for beginners

A black banner titled "AI basics" over the line "How AI models work, which to pick, and how to check them."

This free AI basics course has four short lessons for people who have used a chatbot a few times or never. They cover how large language models work, how to choose a model for a task, why AI makes things up and how to check it, and what chat apps keep from your messages. You need no code and no terminal.

What you'll be able to do

  • Explain in plain words how a language model is trained and why it predicts one token at a time.
  • Say why the same question gets different answers and what a model cannot know.
  • Choose an assistant and a model tier for a task, and test two before you commit.
  • Check an AI answer step by step and match the checking to the stakes.
  • Audit a chat app for training, retention and what never to paste.
All courses

Who it's for

For people who have used a chatbot a few times, or never. You need a chat window on Claude, ChatGPT, Gemini or Copilot. No code, no terminal and no paid plan.

Lessons

  1. 1How do large language models work, in plain words?How large language models work in plain words, shown with real Claude replies: next-token prediction, why answers vary and what a model can't know.10 min
  2. 2Which AI model should I use for my task?Which AI model should I use? Pick the assistant by your task and where your files live, then a fast or deep-thinking model, and test two on your own work.8 min
  3. 3AI hallucinations: why chatbots make things up and how to checkAI hallucinations are fluent answers that are false. See why models make things up, five steps to check an answer and how much checking each task needs.7 min
  4. 4Is it safe to use AI chatbots with personal data? What the apps keepIs it safe to use AI chatbots with personal data? See what the big apps say they keep, how to turn off training, and what never to paste into a chat.8 min

Frequently asked questions

Is this AI basics course free?

Yes. Every lesson in Mindket's Learn section is free to read, and the exercises need only a chat window.

Do I need to know how to code?

No. The course uses no code and no terminal, and every exercise happens in a chat window.

Which AI assistants does the course cover?

It uses Claude, ChatGPT, Gemini and Copilot as examples, with facts from each vendor's own pages. OpenAI's help center did not open when the sources were read, so the lessons cite OpenAI's developer docs and say what they leave out.

How long does the course take?

Each lesson takes about six to eight minutes to read, plus the time you spend on its exercises.

What comes after this course?

The Learn with AI course is next. It shows how to study with a model: study modes, tutor prompts, quizzes and flashcards, and language practice. The prompt engineering course follows it.

Share this course

Write better prompts next

The prompt engineering course teaches prompts, system prompts, context windows and AI agents.

Start prompt engineering

All courses · All articles