AI Fluency Foundations: How LLMs Actually Work

No code, no maths: what a language model is really doing, why it hallucinates, where your data goes, and what it is genuinely good at.

Most people using AI at work have never been told how it works, so they are surprised by the same four problems forever. This is the foundation course that fixes that. You will learn what a language model is actually doing when it answers, why hallucination is structural rather than a bug, how tokens and context windows explain almost every frustration you have had, where your data goes on each tier and what that means under NDAs and the DPDP Act, and a clear-eyed map of what AI is genuinely good and bad at. You will finish with your own written AI operating rules, which is also what an employer's AI-literacy obligation looks like in practice.

What you'll learn

• Explain what a language model is actually doing, without jargon
• Predict and prevent hallucination instead of being surprised by it
• Use tokens and context windows to diagnose why a chat went wrong
• Decide safely what may and may not be pasted into which AI tier
• Judge quickly whether a task suits AI or needs a human
• Write your own AI operating rules and apply them consistently

Course content

1. 1. What a language model is actually doing (15 min)
2. 2. Tokens, context windows, and why long chats go wrong (15 min)
3. 3. Hallucination: why it happens and what reduces it (15 min)
4. 4. Where your data goes: privacy and confidentiality (15 min)
5. 5. What AI is genuinely good and genuinely bad at (15 min)
6. 6. Building your own AI operating rules (15 min)

Related courses

• Prompting That Works: The Universal Framework — One reusable five-part brief that gets usable output from any model, plus the examples, reasoning checks and iteration habits that make it stick.
• Choosing Your AI Stack in 2026 — ChatGPT, Claude, Gemini, Copilot and open-weight models: how to choose on data handling, connections and fit rather than leaderboards.
• AI Agents Explained: From Chatbots to Autonomous Workflows — What an agent really is, what it is genuinely good for in 2026, how to design one you can trust, and how to build your first without code.