AI Foundations

What AI is, what it does, and where it fails.

• What generative AI is
  5 min · Explain what generative AI is and decide which tasks fit it.
• What an LLM actually does
  5 min · Explain how an LLM generates text and what follows from it.
• Tokens, simply
  5 min · Explain tokens and their effect on limits, costs and truncation.
• Context windows
  6 min · Explain what fits in a context window and what happens at the limit.
• Why AI makes things up (hallucinations)
  6 min · Explain why hallucinations happen and catch them before using an answer.
• Models vs products
  6 min · Separate model, product and feature when judging what an AI can do.
• Fast vs reasoning models
  6 min · Choose a fast or reasoning tier based on the shape of the task.
• Why answers vary
  5 min · Explain why outputs vary between runs and keep critical text stable.
• Multimodal AI: text, images, audio
  5 min · Choose the right input type for a task and state its limits.
• Training vs inference: what chats change
  5 min · Explain why a chat does not retrain a model, and what memory features store.
• Tools and function calling, simply
  5 min · Explain how an assistant uses tools, and where the approval gate belongs.
• What an agent is (and isn't)
  6 min · Classify a task as chat, workflow or agent before building anything.