Free course28 lessons · 4 modules
AI basics: a free course on what AI is and how it works
AI Basics is Mindber's free beginner course on artificial intelligence. It answers the questions beginners actually search for, from what AI is to how chatbots, large language models and agents work, in short plain-language lessons that each end with key points and a way to try the idea on real AI tools.
Each lesson answers one question a beginner really asks, such as what a large language model is or what a token means. It opens with a short answer you can use on its own, then explains the idea in plain language, with an example you can try, key points to remember and links to go further.
Take the lessons in order or jump to the one you need. They run from the foundations of AI, through how chatbots and language models work, to using AI well: what it costs, how to choose a tool and where it can go wrong. Every lesson cites primary sources and shows when it was last updated.
What you will learn
- What AI, machine learning, deep learning and generative AI mean, and how they fit together
- How large language models and chatbots such as ChatGPT work, in plain language
- How prompts, retrieval, fine-tuning and agents make AI more useful
- How to judge cost, safety and fit before you choose an AI tool
Course outline
Module 1 · 5 lessons
AI foundations
The core ideas behind modern AI: what it is, how machines learn from data and what generative AI adds.
- What is artificial intelligence (AI)?
Artificial intelligence (AI) is the field of building computer systems that do tasks which normally need human intelligence…
- What is machine learning?
Machine learning (ML) is a branch of artificial intelligence in which computers learn to perform a task from examples instead of…
- What is deep learning?
Deep learning is a type of machine learning that uses neural networks with many layers to learn directly from raw data such as…
- What is a neural network?
A neural network is a computer model made of many simple connected units, called artificial neurons, arranged in layers. Each…
- What is generative AI?
Generative AI is artificial intelligence that creates new content, such as text, images, audio, video or code, in response to a…
Module 2 · 8 lessons
Language models and chat assistants
How large language models and chatbots such as ChatGPT work, and the words used to describe them.
- What is a large language model (LLM)?
A large language model (LLM) is an AI model trained on huge amounts of text to predict which word fragment, or token, comes…
- What is ChatGPT and how does it work?
ChatGPT is an AI chat assistant made by OpenAI and launched on 30 November 2022. You type a question or instruction, and it…
- What is an AI chatbot?
An AI chatbot is software that holds a conversation with you in text or voice and uses artificial intelligence to understand…
- What is a token in AI?
A token is a small piece of text, such as a word, part of a word, a punctuation mark or a space, that a language model reads and…
- What is a context window?
A context window is the maximum amount of text, measured in tokens, that a language model can consider at one time. It holds…
- What are parameters in an LLM?
Parameters are the numbers inside a large language model that it learns during training. Each one is a tiny adjustable weight…
- What is temperature in AI models?
Temperature is a setting that controls how much randomness an AI model uses when it picks each next word. At a low temperature…
- What is an AI hallucination?
An AI hallucination is when an AI model produces information that sounds confident and plausible but is false, made up or not…
Module 3 · 6 lessons
Making AI useful
How people steer, extend and connect AI models with prompts, retrieval, fine-tuning, agents and MCP.
- What is a prompt?
A prompt is the text you give an AI model to tell it what you want: a question, an instruction, or a request plus any context…
- What is RAG (retrieval-augmented generation)?
RAG, short for retrieval-augmented generation, is a way of making an AI model look things up before it answers. The system first…
- What is fine-tuning?
Fine-tuning is extra training that adapts an existing AI model to a specific job. You take a model that has already learned…
- What is an AI agent?
An AI agent is software that uses an AI model to work toward a goal by itself: it decides what steps to take, uses tools such as…
- What is agentic AI?
Agentic AI refers to AI systems designed to act with a degree of independence: given a goal, they plan the steps, use tools to…
- What is the Model Context Protocol (MCP)?
MCP stands for Model Context Protocol, an open standard that defines how AI applications connect to outside tools and data, such…
Module 4 · 9 lessons
Using AI well
The other kinds of AI, and the practical questions: what AI costs, how to choose a tool and whether it is safe.
- What is multimodal AI?
Multimodal AI is AI that can understand or create more than one kind of data, such as text, images, audio and video, in a single…
- What is computer vision?
Computer vision is the field of AI that lets computers interpret images and video: recognising objects, reading text, spotting…
- What is natural language processing (NLP)?
Natural language processing (NLP) is the branch of AI that lets computers work with human language: reading, interpreting…
- What is AGI and how is it different from AI?
AGI, or artificial general intelligence, is a hypothetical AI that could learn and perform almost any intellectual task a person…
- What is open-source AI?
Open-source AI is AI whose building blocks are published so anyone can use, study, modify and share them. For a model, that…
- How much does AI cost?
AI can cost nothing or add up to a substantial monthly bill, depending on how it is priced and how much you use it. Consumer…
- How do you choose an AI tool?
Choose an AI tool by starting from the job, not the tool. Write down the task, who will use it and what a good result looks…
- Is AI bad for the environment?
AI does have an environmental cost, mainly the electricity and water used by data centres to train and run models, plus the…
- Is AI safe to use?
AI is generally safe for everyday tasks if you treat it as a capable but fallible assistant. The main risks are confident wrong…
Frequently asked questions
Is the AI Basics course really free?
Yes. Every lesson is free to read and needs no account or sign-up. The examples are plain text you can copy into the AI assistant of your choice, and the links into Mindber open the directory, rankings and calculators, which are free to browse.
Do I need a technical background?
No. The lessons assume no maths and no programming. Technical words are explained when they first appear, and each lesson opens with a short answer you can read on its own. A few lessons include a small code sample, and you can skip it without losing the thread.
Where should I start, and how long does it take?
Start with lesson 1 for the full picture, or use the search on the learning hub to jump to the question you have. Each lesson takes only a few minutes to read, so you can finish the course over a few short sessions or read just the lessons you need.
Last updated