AI Fundamentals

What is AI, and What is Generative AI?

Modern AI systems learn patterns from huge amounts of data — generative AI is the subset that produces new content (text, images, code) rather than just classifying or predicting.

Prompt Engineering: The Basics

A prompt is the instruction you give an AI system — and the difference between a vague prompt and a specific one is often the difference between a useless answer and a great one.

Context, Constraints, and Output Format

Three specific levers turn a decent prompt into a great one: giving background the AI wouldn't otherwise have, boxing in the answer's shape, and specifying exactly how the output should look.

Working with AI APIs (Conceptually)

An AI API lets your own application send a prompt and receive a generated response — the same request/response pattern as any other web API, with a few AI-specific details.

AI Agents & Automation

An AI agent doesn't just answer one question — it can take actions, check the results, and decide what to do next, in a loop, toward a goal.

AI Hallucinations: When Confident Answers Are Wrong

An AI can state something completely false with the exact same confident tone it uses for something true — learning to spot and reduce these "hallucinations" is one of the most important AI literacy skills there is.

Brainstorming vs. Facts: Knowing Which Mode You're In

AI is at its best generating options, angles, and ideas — and at its riskiest when those same outputs get treated as verified facts. Knowing which mode you're in changes how you should read the answer.

An Introduction to AI Image Generation

Text-to-image models turn a written description into a picture that never existed before — the same "be specific" instinct from text prompting applies, with a few new levers unique to images.

Ethical Considerations: Bias, Over-Reliance, and When Not to Use AI

AI tools inherit the biases and gaps of the data they were trained on, can quietly erode a skill if leaned on too heavily, and simply aren't the right tool for every situation — knowing the limits matters as much as knowing the capabilities.

What Does "Training a Model" Actually Mean?

Every LLM starts out as a blank slate of random numbers — "training" is the long, repetitive process of adjusting those numbers, one small correction at a time, until the model gets good at predicting text.