AI automation glossary

A large language model (LLM) is an AI system trained on huge amounts of text to understand and generate human language.

A system prompt is the instruction that defines an AI agent's role, rules, and behaviour before any conversation begins.

Agentic automation is automation where an AI agent decides how to complete a task, instead of following a fixed set of rules.

AI operations means running everyday business processes with AI agents and automation instead of manual effort.

An AI agent is software that pursues a goal on its own.

An AI copilot is an assistant that helps a person as they work — suggesting text, drafting, or answering in real time — while the human stays in control and approves each step.

An AI employee is an AI agent configured to own a recurring role rather than answer one-off questions.

Multi-agent orchestration is coordinating several specialized AI agents to complete one goal together.

Multi-provider AI means your agents can run on any model provider — such as Anthropic's Claude, OpenAI's GPT, or DeepSeek — instead of being tied to one.

No-code automation lets people build automations by connecting apps in a visual interface instead of writing code.

Retrieval-augmented generation (RAG) is a technique where an AI looks up relevant information before answering, then uses it to write the response.

Self-hosted AI means running AI agents and automation on infrastructure you control — your own servers or cloud account — rather than only a vendor's platform.

The Model Context Protocol (MCP) is an open standard that lets AI agents connect to external tools and data through one common interface.

Tool calling is how an AI agent takes action instead of only producing text.

Workflow automation runs a fixed sequence of steps across your apps automatically.