Working with AI: The Basics
How AI assistants work on the inside: from how a model writes an answer to how to give it tasks and check the result. No programming is needed.
Already studying on another device? Sign in with a key
How to take the course
On your own
Read the lessons in order and answer the questions at the end of each one. Your progress is saved automatically.
With Agnes
Every lesson page has a course assistant. Select a passage you find unclear and ask: Agnes answers from the course materials.
With your own AI agent
Give your assistant a prompt with a link to the course text: it will take you through the lessons and check that everything is clear.
See the prompt and the links for an agent
You are my teacher for the course “Working with AI: The Basics” from the school promt.engineer. Course materials: https://promt.engineer/en/llms.txt lists the eight lessons with links to their text. Open the lessons one at a time, in order, and rely only on their text. If something is not in a lesson, say so. How we work: 1. Before each lesson, tell me in two or three sentences what it is about and why it matters at work. 2. Explain the lesson section by section, in your own words, with examples from my work: [briefly describe what you do]. 3. After each section, ask me one question to check my understanding and wait for my answer. If I am wrong, explain exactly where. 4. At the end of the lesson, go through its self-check questions: let me answer first, then compare my answer with the lesson’s. 5. Move on to the next lesson only when I write “next”. Write in English, briefly and without introductions. Start with the first lesson.
Course text for agents: promt.engineer/en/llms.txt. If the assistant does not open links, attach the whole course as one file to the prompt.
Lessons take them in order or pick the one you needall lessons stay open, and you can return to any of them
-
Lesson 1How a language model writes an answer
What happens between a question and its answer?
-
Lesson 2Tokens: the pieces the model builds text from
Why does the model get confused counting letters, and why are limits counted in tokens?
-
Lesson 3 · nowChat and memory: what the model remembers from a conversation
Why does the model remember the start of a conversation but forget everything in a new chat?
Continue reading → -
Lesson 4What the model knows and where its mistakes come from
Where does the model get its facts, and why does it sometimes make them up?
-
Lesson 5Tools and agents: how the assistant takes actions
How does an assistant read files, run code and carry out multi-step tasks on its own?
-
Lesson 6Reasoning: what it means when “the model is thinking”
When does reasoning help, and when does it only cost time and money?
-
Lesson 7Checking the result: how to tell whether you can trust an answer
How can you tell whether you can trust an answer?
-
Lesson 8How to give the model a task
How do you write a request that gets you what you need the first time?