Glossary

AI Glossary

Plain-language meanings of the words you keep hearing.

AI agent: An AI system that plans steps, uses tools and acts to complete a goal, rather than only replying with text.
API: A way for programs to talk to each other. Developers use AI APIs to add models to their own apps.
Artificial intelligence (AI): Computer systems that perform tasks we usually associate with human intelligence, such as understanding language, recognising images or making decisions.
Chatbot: An app you talk to in natural language. Modern chatbots are usually powered by large language models.
Context window: How much text a model can consider at once, including your messages, files and its own reply.
Embedding: A list of numbers that represents the meaning of text or images, so similar things end up close together. Used for search and recommendations.
Fine-tuning: Extra training on a smaller, specific dataset to adapt a model to a task, style or domain.
Generative AI: AI that creates new content (text, images, audio, video or code) rather than only classifying existing data.
Hallucination: When an AI confidently states something false or made up. Always verify important facts.
Inference: Using a trained model to produce an output, such as answering your question.
Large language model (LLM): An AI model trained on huge amounts of text to predict the next token. LLMs power chatbots like ChatGPT, Claude and Gemini.
Machine learning: A branch of AI where systems learn patterns from data instead of following hand-written rules.
Multimodal: A model that works with more than one type of input or output, for example text, images and audio.
Neural network: A model made of layers of connected units, loosely inspired by the brain. Deep learning uses neural networks with many layers.
Open-weight model: A model whose trained parameters are published, so anyone can download and run it, including on their own computer.
Parameters: The internal numbers a model learns during training. Model size is often described by its number of parameters.
Prompt: The instruction or question you give an AI model. Clear prompts with context and a desired format get better results.
RAG (retrieval-augmented generation): A technique where the system first searches relevant documents, then gives them to the model so its answer is grounded in sources.
Token: A small chunk of text (often part of a word) that language models read and write. Usage limits and prices are usually counted in tokens.
Training: The process of teaching a model by showing it data and adjusting its parameters to reduce mistakes.