The AI Glossary, without the jargon
The AI terms that actually matter — explained simply, in plain English. No CS degree required.
Basics
AI (Artificial Intelligence)
Software that can learn patterns and make decisions or create content, instead of just following fixed rules.
Generative AI
AI that creates new things — text, images, code, audio — rather than just analysing existing data.
LLM (Large Language Model)
The kind of AI behind tools like Claude and ChatGPT — trained on huge amounts of text to understand and generate language.
Model
The trained 'brain' an AI tool runs on. Different models are better at different tasks.
Chatbot
An AI you talk to in plain language to get answers or help.
Using AI
Prompt
The instruction you give an AI to tell it what you want.
Prompt Engineering
The skill of writing clear prompts that get reliable, useful results. No coding needed.
System Prompt
A behind-the-scenes instruction that sets how the AI should behave throughout a conversation.
Few-shot Examples
Showing the AI a few examples of what you want so it follows the same pattern.
Chain-of-thought
Asking the AI to reason step by step, which usually gives more accurate answers.
Context Window
How much text an AI can 'keep in mind' at once — the conversation and documents it can consider.
Token
The small chunks of text an AI reads and writes. They affect cost and length limits.
Hallucination
When an AI confidently says something that is wrong. Always verify important facts.
Building
Vibe Coding
Building software by describing what you want in plain language and letting AI write the code.
No-code
Building apps and tools without writing code yourself.
Automation
Letting AI or software do repetitive tasks for you automatically.
AI Agent
An AI that can take a goal and carry out multiple steps on its own to achieve 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 your own documents to answer from, so it uses your data, not just what it was trained on.
Deploy
Putting your project online so other people can actually use it.
Under the hood
Machine Learning
Teaching computers to learn from examples instead of being given exact rules.
Neural Network
A type of model loosely inspired by the brain, used to recognise complex patterns.
Training Data
The examples an AI learns from. Its quality shapes how good the AI is.
Fine-tuning
Adapting an existing model to a specific task with extra examples.
Inference
The moment an AI actually produces an answer from your input.
Multimodal
AI that can work with more than one type of input — text, images, audio, and more.
Open-source Model
A model anyone can download, use, and modify freely.
Safety & Ethics
Bias
When an AI's answers unfairly favour or disadvantage certain groups, often from its training data.
Deepfake
AI-generated fake images, video, or audio made to look real. A reason to verify what you see online.
Responsible AI
Using AI honestly and safely — checking facts, respecting privacy, and not misusing it.
Ready to use these for real?
Come to a free workshop, see what AI can build, and get your roadmap. No code, no jargon.
Book a Free Workshop