AI glossary: key terms explained
The Mindber AI glossary defines the terms you meet when choosing and using AI tools, from large language models to retrieval. Each definition opens with a one-sentence answer, then adds context, related terms and primary sources.
A
- Agentic AI
Agentic AI describes AI systems that act with a degree of autonomy to achieve goals: they plan, take actions through tools, adapt to results and…
- AI acceptable use policy
An AI acceptable use policy is a document that tells employees how they may and may not use AI tools at work: which tools are approved, what data…
- AI agent
An AI agent is software that uses an AI model to pursue a goal over multiple steps with some autonomy. It decides what to do next, calls tools such…
- AI detector
An AI detector is a tool that estimates whether a piece of text, image, audio or video was generated by AI. Text detectors analyse statistical…
- AI governance
AI governance is the framework of policies, processes, roles and controls an organisation uses to ensure its development and use of AI is safe…
- AI workflow automation
AI workflow automation is the use of AI models inside automated business processes, connecting apps, triggers and rules so that tasks run with…
C
- Chain-of-thought prompting
Chain-of-thought (CoT) prompting is a technique that asks a language model to work through intermediate reasoning steps before giving a final…
- Context window
A context window is the maximum amount of text, measured in tokens, that a language model can take into account at one time. It includes the system…
E
- Embedding
An embedding is a list of numbers (a vector) that represents the meaning of a piece of data, such as a word, sentence, image or document. Items with…
F
- Few-shot prompting
Few-shot prompting is a technique in which you include a small number of worked examples of a task in the prompt, so the model can infer the pattern…
- Fine-tuning
Fine-tuning is the process of further training an existing AI model on a smaller, task-specific dataset so it adapts its behaviour, style or format…
- Foundation model
A foundation model is a large AI model trained on broad data at scale that can be adapted to many different tasks, such as writing, coding, image…
G
- Generative AI
Generative AI is a type of artificial intelligence that creates new content, such as text, images, audio, video or code, based on patterns learned…
H
- Hallucination
In AI, a hallucination is output that sounds plausible but is false, unsupported by the model's sources or entirely made up, such as an invented…
I
- Inference
Inference is the stage where a trained AI model is used to produce output: it takes an input, such as a prompt or an image, and generates a…
L
- Large language model (LLM)
A large language model (LLM) is an AI model trained on very large amounts of text to predict the next token in a sequence. That simple objective…
M
- Model Context Protocol (MCP)
The Model Context Protocol (MCP) is an open standard, introduced by Anthropic in November 2024, for connecting AI applications to external tools and…
- Multimodal AI
Multimodal AI refers to models that can understand or generate more than one type of data, such as text, images, audio and video, within a single…
O
- Open-weight model
An open-weight model is an AI model whose trained parameters (weights) are published for anyone to download, run and often fine-tune on their own…
P
- Prompt
A prompt is the input you give an AI model to tell it what to do: a question, an instruction, context, examples or a file. The model generates its…
R
- Reasoning model
A reasoning model is a language model trained to work through a problem in intermediate steps before giving its final answer, a process often called…
- Retrieval-augmented generation (RAG)
Retrieval-augmented generation (RAG) is a technique that gives a language model relevant information from an external source, such as company…
S
- Seat-based pricing
Seat-based pricing is a billing model in which a software vendor charges a fixed fee per user, or seat, usually per month or year. Many AI business…
- Shadow AI
Shadow AI is the use of AI tools, models or features at work without the knowledge, approval or oversight of an organisation's IT, security or…
- System prompt
A system prompt is a set of instructions given to an AI model before the conversation begins, defining its role, tone, rules and output format for…
T
- Temperature
Temperature is a setting that controls how random a language model's output is. Low values make the model pick the most likely tokens, giving…
- Text-to-video
Text-to-video is a type of generative AI that creates video clips from a written description, or prompt. The model generates frames that match the…
- Token
A token is the basic unit of text a language model reads and writes. Tokenizers split text into tokens, which can be whole words, parts of words…
- Token-based pricing
Token-based pricing is a billing model in which an AI provider charges for the number of tokens a model processes, usually quoted per million…
- Tool calling
Tool calling, also known as function calling, lets a language model request an action from external software by producing a structured call, such as…
- Transformer
The transformer is a neural network architecture, introduced in the 2017 paper "Attention Is All You Need", that processes sequences using a…
V
- Vector database
A vector database stores embeddings, the numerical representations of text, images or other data, and finds the stored items most similar to a query…
Last updated