AI Glossary: Plain-Language Definitions

A

Agentic AI Agentic AI is AI that plans and executes multi-step tasks on its own, deciding what to do next, using tools, and adjusting, with limited human input.
AI Agent An AI agent is an AI system that plans and executes multi-step tasks using tools, not just answering questions. What that means for your team.
AI Copilot An AI copilot is an assistant embedded in the software you already use, drafting and suggesting alongside you while you keep control of the result.
AI Governance AI governance is the policies, roles, and controls an organization uses to make sure its AI use is safe, legal, and accountable.

Chain-of-Thought Chain-of-thought is when an AI model works through a problem step by step before answering, improving accuracy on math, logic, and multi-step tasks.
Context Window A context window is the maximum amount of text, measured in tokens, an AI model can consider at once, including your prompt, documents, and its reply.

Embedding An embedding is a list of numbers that represents the meaning of text, so software can measure how similar two pieces of content are.

Few-Shot Prompting Few-shot prompting means showing an AI model a handful of worked examples inside your prompt so it copies the pattern instead of guessing the format.
Fine-Tuning Fine-tuning is additional training that adapts a pre-trained AI model to a specific task, style, or domain. When it's worth it, and when it isn't.
Foundation Model A foundation model is a large AI model trained on broad data that serves as a general-purpose base adapted to many different tasks and products.
Function Calling Function calling lets an AI model request that your software run a specific action, look up an order, send an email, instead of only writing text.

Generative AI Generative AI is AI that creates new content, text, images, code, audio, video, rather than only analyzing or classifying what already exists.
Grounding Grounding means anchoring an AI model's answers in verifiable source material, your documents, live data, or the web, instead of memory alone.
Guardrails Guardrails are the controls placed around an AI system to keep its behavior safe and on-policy, filtering inputs, constraining outputs, blocking misuse.

AI Hallucination An AI hallucination is when a model confidently generates false information. Why it happens, what it looks like at work, and how teams defend against it.

Inference Inference is running a trained AI model to get an output, every prompt you send triggers inference, and it's what AI usage bills actually charge for.

Knowledge Cutoff A knowledge cutoff is the date after which an AI model's training data ends, the model knows nothing that happened later unless you provide it.

Large Language Model (LLM) A large language model (LLM) is an AI system trained on massive text data to understand and generate language. What it means for how you work.

Machine Learning Machine learning is the field of AI where systems learn patterns from data and improve with examples, instead of following hand-written rules.
Model Context Protocol (MCP) Model Context Protocol (MCP) is an open standard that lets AI assistants connect to tools and data sources, one connector, usable by any AI app.
Multimodal AI Multimodal AI is AI that works across more than one kind of input or output, text, images, audio, video, in a single model or system.

Natural Language Processing (NLP) Natural language processing (NLP) is the field of AI focused on understanding and generating human language, the technology behind chatbots and translation.

Prompt Engineering Prompt engineering is the practice of writing instructions that get reliable, high-quality output from AI models. The core techniques, in plain language.
Prompt Injection Prompt injection is an attack that hides instructions in content an AI processes, a web page, email, or document, to hijack the AI's behavior.

Retrieval-Augmented Generation (RAG) Retrieval-augmented generation (RAG) lets an AI look up your documents before answering, grounding responses in real sources instead of memory alone.

Structured Output Structured output is AI-generated data in a fixed, machine-readable format, like JSON matching a schema, so software can use it without a human reading it.
System Prompt A system prompt is the standing instruction set an AI model receives before any user message, defining its role, rules, tone, and boundaries.

Temperature Temperature is a setting that controls how random an AI model's word choices are, low for consistent, predictable output; high for varied, creative output.
Token A token is the small chunk of text, roughly three-quarters of a word, that AI language models read, generate, and bill by.

Vector Database A vector database stores embeddings, numerical representations of meaning, and finds the most similar items fast, powering AI search over your content.