AI Basics in AI Engineering

Every AI Basics lesson in the AI Engineering course, in the order you study them. Each page opens about the first half of its lesson to read, some the whole of it; the full lessons and their workbooks are in the plan.

8 lessons

  1. Start here: LLM literacy without code

    Learn how AI works without writing code: who the route is for, how the depth levels work, the lessons in order, and how to study without code.

  2. How a chatbot works: next-token prediction, sampling temperature and the context window

    How AI chatbots work without the code: a very good guesser of the next token, why the same question gets different answers, and what it remembers.

  3. Hallucination: plausibility, confidence and correctness

    Why AI hallucinates: plausible is not the same as true, a test with made-up questions, why confidence is not correctness, and how to protect yourself.

  4. Prompting from the mechanism: document continuation and in-context examples

    Prompt engineering explained from how models work: a prompt is the start of a document, three ways to ask measured, and why examples work so well.

  5. Workplace AI risk: data exposure, prompt injection and checking outputs

    Using AI at work safely: confident wrong answers, where pasted data goes, instructions hidden in documents, and how to check output without redoing it.

  6. Agents without code: long-horizon failure and permission scope

    AI agents without code: what an agent is, why long tasks fail as steps add up, a real agent measured, and what an agent should be allowed to touch.

  7. Reading AI claims: benchmarks, contamination and demos

    How to read AI benchmarks and news: scores, demos and forecasts, why a 2-point lead can be noise, what a benchmark measures, and six questions to ask.

  8. Project: an AI adoption plan for your role

    Make an AI plan for your job: choose a frequent, low-stakes, easy-to-check task, write the plan, try it on ten real examples and grade the result.