Free · No sign-up · Open source

AI, agents and models, explained in five minutes.

Plain words, one clear diagram, and a source behind every fact.

Today in AI

Sat, 24 Oct 2026

I'm new to AI Start with the basics. No maths or code.I know the basics Go deeper: how models work, how to build with them, how to run them.

From the catalogue

An AI system infers from received inputs how to generate predictions, content, recommendations or decisions for explicit or implicit objectives.

An LLM predicts a token or sequence of tokens, sometimes many paragraphs long.

An embedding maps a discrete item such as a token ID to a dense vector of numbers.

RAG lets an AI model look up relevant documents first, then answer from what it found.

An AI agent is a language model that chooses its own next steps and tools while it works through a task.

MCP standardizes how AI applications connect to external context and tools.

29 short chapters, from what AI is to running it safely. Start with any part.

The method

Get the answer in fifteen seconds. Stay for the why, the how, the real uses and the limits.