AI glossary: the words everyone's using, explained simply

An AI agent is an AI system that can take actions to reach a goal, not just reply with text.

An AI API lets your software send a request to an AI model over the internet and get a response back, so you can add AI features to an app without running the model yourself.

AI bias is when an AI system gives unfair or skewed results for certain groups of people, usually because of patterns in its training data or how it was designed.

An AI chatbot is a program you talk to in everyday language that replies like a person would.

AI evals are tests that measure how well an AI system performs on a set of example inputs with known good answers.

An AI hallucination is when an AI model states something false or made up as if it were true, such as a fake fact, quote, statistic or source.

Artificial intelligence (AI) is software that performs tasks that usually need human intelligence, like recognising faces, translating languages or answering questions.

Attention is the mechanism in transformer models that lets each word look at every other word in the text and decide which ones matter most for understanding it.

Chain-of-thought prompting asks an AI model to work through a problem step by step before giving the final answer.

Computer vision is the field of AI that lets computers understand images and video, such as recognising faces, reading text, detecting objects or spotting defects.

A context window is the maximum amount of text, measured in tokens, that an AI model can consider at one time, including your messages, any documents you paste, and its own replies.

Deep learning is a kind of machine learning that uses neural networks with many layers.

A deepfake is a fake video, image or audio clip made with AI to look or sound like a real person saying or doing something they never did.

Embeddings are lists of numbers that represent the meaning of text, images or other data, so that similar things get similar numbers.

Few-shot prompting means including a few examples of the input and the output you want inside your prompt, so the AI copies the pattern.

Fine-tuning is further training of an existing AI model on a smaller, specific set of examples, so it gets better at a particular task, style or domain.

Generative AI is AI that creates new content, such as text, images, audio, video or code, instead of only sorting or predicting labels.

A large language model (LLM) is an AI model trained on huge amounts of text to predict the next word.

Machine learning (ML) is the part of AI where computers learn from data instead of being explicitly programmed.

Multimodal AI is AI that can understand or create more than one kind of data, such as text, images, audio and video, in the same conversation.

Natural language processing (NLP) is the field of AI focused on understanding and generating human language: translation, summarising, sentiment, speech and chat.

A neural network is a machine learning model made of layers of simple connected units, loosely inspired by the brain.

A prompt is what you type to an AI tool to tell it what you want: a question, an instruction, examples or background.

Prompt engineering is the practice of designing and testing prompts so an AI model reliably gives the output you need.

Retrieval-augmented generation (RAG) is a way to make an AI answer from specific, trusted documents.

A system prompt is a set of instructions given to an AI model before the conversation starts, setting its role, rules and style for every reply.

Temperature is a setting that controls how random an AI model's output is.

A token is a small piece of text that a language model reads and writes, often part of a word.

Training data is the collection of examples an AI model learns from, such as labelled photos, text or past decisions.

A transformer is the neural network design behind modern language models like the ones in ChatGPT, Gemini and Claude.

A vector database stores embeddings and quickly finds the ones closest to a query embedding.

Vibe coding is building software by describing what you want to an AI coding tool in plain language, then testing and refining what it produces, instead of writing all the code yourself.