Reference
Plain-English definitions of the AI terms that actually matter.
Artificial Intelligence is the field of building computer systems that perform tasks normally requiring human intelligence, such as understanding language, recognizing images and making decisions.
A Large Language Model is a neural network trained on vast amounts of text that can generate, summarize and reason about language. Examples include GPT, Claude and Gemini.
A token is a chunk of text — roughly 4 characters or three-quarters of a word — that language models use as their basic unit of processing and billing.
The context window is the maximum amount of text (measured in tokens) a model can consider at once, including both the prompt and its response.
A hallucination is when an AI model produces information that sounds plausible but is factually incorrect or fabricated.
Multimodal AI refers to models that can understand and generate more than one type of data — for example text, images, audio and video together.
Prompt engineering is the practice of designing and refining the instructions given to an AI model to get accurate, useful and consistent results.
An AI agent is a system that uses an AI model to autonomously plan and execute multi-step tasks, often calling tools, APIs or other agents to reach a goal.
MCP is an open standard that lets AI applications connect to external tools and data sources through a consistent interface.
RAG is a technique that retrieves relevant documents from a knowledge base and feeds them to an LLM so its answers are grounded in specific, up-to-date data.
Fine-tuning adapts a pre-trained model to a specific task or domain by training it further on a smaller, specialized dataset.
An embedding is a numerical vector representation of text or data that captures meaning, enabling semantic search and similarity comparisons.