AI Glossary for Non-Tech Students: 28 Terms Explained Simply

Core ideas

• Artificial Intelligence (AI): Software that performs tasks that normally need human intelligence, such as understanding language, recognising images or making predictions.
• Generative AI: AI that creates new content — text, images, audio, video or code — from a prompt.
• Large Language Model (LLM): An AI model trained on huge amounts of text to understand and generate language. Claude, GPT and Gemini are LLMs.
• Prompt: The instruction or question you give an AI tool.
• Prompt engineering: Writing prompts with clear context, constraints and examples so the AI gives reliable, useful output.
• Token: A small chunk of text (roughly ¾ of a word) that AI models read and write. Usage limits and pricing are counted in tokens.
• Context window: How much text an AI model can consider at once — your prompt, documents and the conversation so far.
• Hallucination: When AI states something false with confidence, such as an invented citation. Always verify facts that matter.

Building with AI

• AI agent: An AI system that can plan steps and use tools — search, spreadsheets, email — to complete a goal, not just answer one question.
• Multi-agent system: Several AI agents with different roles working together on a task.
• Automation workflow: A chain of steps (e.g. form → AI → sheet → email) that runs without manual work. Tools: n8n, Zapier, Make.
• No-code: Building apps and automations through visual tools instead of writing code.
• Vibe coding: Describing what you want in plain language and letting AI write the code, while you test and direct it.
• API: A way for one piece of software to talk to another — how apps connect to AI models.
• RAG (Retrieval-Augmented Generation): Giving an AI model relevant documents at question time so its answers are grounded in your sources.
• Fine-tuning: Further training a model on specific examples to change its behaviour or style.
• Embedding: A numeric representation of meaning that lets software find similar text, images or documents.

Using AI responsibly

• AI literacy: Knowing what AI can and can't do, how to use it effectively, and how to check its output.
• Bias: Systematic unfairness in AI outputs, often inherited from training data.
• Human-in-the-loop: A workflow where a person reviews or approves AI output before it is used.
• Guardrails: Rules and checks that keep an AI tool within safe, intended behaviour.
• Data privacy: Protecting personal information — never paste confidential or identifiable data into public AI tools.

Search & visibility

• SEO (Search Engine Optimisation): Making content easy for search engines like Google to find and rank.
• AEO (Answer Engine Optimisation): Structuring content so AI assistants and search features quote it directly as the answer.
• GEO (Generative Engine Optimisation): Making your brand and content likely to be cited by generative AI tools such as ChatGPT, Perplexity and Google AI Overviews.

Careers

• AI-native professional: Someone who uses AI as a default part of their daily work in any field — law, finance, design or marketing.
• AI product manager: A person who decides what an AI product should do and for whom, and works with builders to ship it.
• AI portfolio: A collection of real projects you built with AI, with the problem, process and results — stronger evidence than a certificate.