Glossary

AI automation glossary

The terms you’ll hear when people talk about AI in business, explained in a sentence or two, with an example.

AI agent

An AI agent is software that uses a large language model to understand a request or goal, decide what steps to take, and carry them out using tools such as booking systems, databases, email or a CRM, usually with limits and human checkpoints.

AI automation audit

An AI automation audit is a structured review of a business's processes, tools and data that identifies which tasks AI and automation can take over, estimates the time and money each would save, and puts them in a practical order of priority.

AI chatbot

An AI chatbot is a program that holds a natural-language conversation, by text or voice, using a large language model to understand questions and generate answers. In business, it is usually limited to answering from the company's own approved information.

API integration

An API integration is a connection between two software applications through their application programming interfaces (APIs), so they can send and receive data automatically, for example creating an invoice in your accounting tool when a deal closes in your CRM.

Human-in-the-loop

Human-in-the-loop (HITL) is a design approach where a person reviews, approves or corrects an AI system's output at defined points, especially before actions that are costly, irreversible, sensitive or regulated.

Large language model (LLM)

A large language model (LLM) is an AI system trained on very large amounts of text to predict and generate language. That lets it answer questions, summarise, draft, classify and translate. GPT, Claude, Gemini and Llama are examples.

No-code automation

No-code automation means building automated workflows with visual, drag-and-drop tools such as Zapier, Make or n8n instead of writing code, by choosing a trigger and the actions that should follow.

Prompt engineering

Prompt engineering is the practice of writing and testing the instructions given to an AI model, including its role, context, task, constraints and output format, so that it produces accurate, consistent and useful results.

RAG (retrieval-augmented generation)

Retrieval-augmented generation (RAG) is a technique in which an AI system first searches a specific set of documents, such as your policies, FAQs or contracts, for relevant passages, and then writes its answer using only those passages, ideally with citations.

Workflow automation

Workflow automation is the use of software to run a repeatable business process automatically, starting from a trigger such as a form submission, new order or date, and moving information between apps without someone copying it by hand.