AI Glossary: Plain-English Terms for Professionals
Short, simple explanations of the AI words you will hear at work, each with an everyday example.
Last updated: 13 November 2026
Resources / Glossary · By the MoneyTrees team
Terms
Artificial intelligence (AI)
Software that can do tasks that usually need human thinking, like writing, recognising images or making predictions.
Example: A tool that drafts an email reply for you.
Generative AI
AI that creates new content — text, images, audio or code — from your instructions.
Example: Asking for a poster caption and getting three options.
Large language model (LLM)
The type of AI behind ChatGPT, Gemini and Claude. It learned patterns from huge amounts of text and predicts useful words in reply.
Example: ChatGPT answering a question in full sentences.
Prompt
The instruction or question you give an AI tool.
Example: 'Summarise this report in 5 bullets.'
Prompt engineering
Writing prompts clearly and in a structured way so the AI gives reliable, useful answers.
Example: Adding a role, context and format to your request.
Hallucination
When AI states something false or made up as if it were true.
Example: Inventing a statistic or a source that does not exist.
Context window
How much text the AI can consider at once — your prompt, pasted documents and the conversation so far.
Example: A very long document may need to be split into parts.
Token
A small chunk of text (roughly part of a word) that AI tools count for limits and pricing.
Example: Longer prompts and answers use more tokens.
AI agent
An AI setup that can take several steps on its own, like searching, using tools and completing a task.
Example: An assistant that finds meeting times and sends invites.
RAG (retrieval-augmented generation)
A method where AI first looks up information from your documents, then answers using it.
Example: A support bot that answers from your company's help pages.
Automation workflow
A set of steps that run automatically when something happens, sometimes using AI in between.
Example: A new form entry creates a draft reply for review.
Fine-tuning
Training an existing AI model further on specific examples so it behaves in a particular way.
Example: A model trained on a company's tone for customer replies.
Go further
Learn the full method in the AI Prompt Engineering Masterclass, or browse all courses.
More free material: Free AI Prompts for Work · Prompt Engineering for Beginners: A No-Code Guide · How Indian Professionals Can Use AI at Work: A Practical Guide
Editorial note: these prompts and explanations are written and reviewed by the MoneyTrees team for general learning. AI output can be wrong — always check facts, numbers and company policy before using it.