The model is finishing your sentence.
Stop treating every AI feature like the same magic trick. Learn what models can do, when they need your documents, and when a simple prompt beats building an agent. Free, with a lab and a quiz. No sign-in and no email. When you want the architecture practice or the agent project, those are the Pro courses.
What a language model is doing
A model continues text. The product around it is a separate purchase.
Open →02 · lesson · 5 minTokens and the context window
The bill and the memory of one request are both counted in tokens, not in words.
Open →03 · lesson · 5 minAgents and RAG
Retrieval puts pages in the prompt. An agent is a loop that can call a tool and read the result.
Open →04 · lesson · 5 minFine-tuning, and when to leave it alone
Fine-tuning changes the model with more training. It is a poor substitute for a document you could have pasted.
Open →05 · lesson · 8 minFive AI tools: our verdicts, and where to find today's prices
Use or Watch for five popular AI tools, with a link to each one's live pricing page. Prices change often, so we don't print them here.
Open →06 · lab · 40 minLab: name the mechanism, then catch a model without the page
Three jobs, a public tokenizer, and a chat demo that proves a missing paragraph is a missing source.
Open →07 · worksheet · 10 minWorksheet: AI literacy checklist
A one-page checklist: how AI models work, what they can see, which approach fits a job, and which tools we recommend.
Open →Quiz · 12 scenariosCan you spot what the task actually needs?
Try the scenario quiz. A score of 75% meets this course’s practice threshold. The explanations show what you missed.
Take the quiz →The one-page architect cheat sheet is a free study map. The Pro courses add the practice questions, the mock, and the agent lab.
For each tool recommendation, check the linked pricing page for the current plans and limits. The directory profiles are dated public notes, not hands-on benchmarks.