Glossary
AI terms, explained simply
Short, plain-English definitions of the words you will meet when working with AI.
A
- AI Agent
- An AI system that plans and carries out multi-step tasks using tools, and why good agents have limits and human approval.
C
- Context Window
- The amount of text an AI model can consider at once, why long chats forget instructions and how to work within the limit.
H
- Hallucination
- When an AI states something false or invented as if it were true, with examples and practical ways to reduce the risk.
L
- Large Language Model (LLM)
- An AI system trained on large amounts of text to understand and generate language, and how it differs from a chatbot or search engine.
M
- MCP (Model Context Protocol)
- An open standard that lets AI assistants connect to external tools and data, with key terms and safety basics.
P
- Prompt
- The instructions and input you give an AI model to tell it what to do, with a vague-versus-clear example.
R
- RAG (Retrieval-Augmented Generation)
- A technique where an AI retrieves relevant documents first and answers using them, with the steps, benefits and limits.
S
- System Prompt
- Standing instructions that set an AI model's role, tone and rules before a conversation starts, and what makes a good one.
T
- Temperature
- A setting that controls how predictable or varied an AI model's output is, with guidance on low, medium and high values.
- Token
- A small chunk of text that AI models process, why limits and prices are counted in tokens and rough sizes in English.