Glossary of AI and automation terms
One-sentence definitions of the terms used across the site.
A
- AI agent
- An AI agent is a software system that uses an AI model to choose its own steps and tools in order to reach a goal that a person has set.
- AI assistant
- An AI assistant is a software tool that helps a person complete tasks by understanding requests in ordinary language and responding with an answer, a draft or an action.
- API
- An application programming interface (API) is a set of rules that lets one piece of software request data from, or send instructions to, another.
- Artificial intelligence
- Artificial intelligence (AI) is software that infers, from the input it receives, how to generate outputs such as predictions, content, recommendations or decisions.
- Automation
- Automation is the use of software or machines to carry out a task with little or no human action at each step.
C
- Chatbot
- A chatbot is a program that people communicate with through text or voice in a chat interface, which answers questions or completes simple tasks.
- Conversational AI
- Conversational AI is the set of technologies that let people talk with software in ordinary language, by text or speech, and receive replies that fit the conversation.
E
- Execution
- In n8n, an execution is one complete run of a workflow from its trigger to its last step, however many steps the workflow contains.
G
- Generative AI
- Generative AI is artificial intelligence that produces new content, such as text, images, audio or code, in response to a prompt.
H
- Hallucination
- In AI, a hallucination is an output that reads as plausible but is false or not supported by the input or any real source.
- Human in the loop
- Human in the loop describes a workflow design in which a person reviews or approves selected steps or outputs before they take effect.
L
- Large language model
- A large language model (LLM) is an AI model trained on very large amounts of text to predict and generate language, which lets it answer questions, summarise, classify and draft text.
M
- Machine learning
- Machine learning is a method in which a program or system trains a model from input data, so it can make predictions or decisions on new data.
P
- Prompt
- A prompt is the instruction or question given to an AI model, which shapes what it produces.
R
- Retrieval-augmented generation
- Retrieval-augmented generation (RAG) is a technique in which a system looks up relevant information in a set of documents and gives it to a language model, which then writes the answer from it.
- Robotic process automation
- Robotic process automation (RPA) is software that operates other programs through their screens, copying the clicks and keystrokes a person would use to complete a routine task.
T
- Trigger
- A trigger is the event that starts an automated workflow, such as a message arriving, a form being submitted or a set time being reached.
W
- Webhook
- A webhook is a web address that one system calls to send information to another system as soon as an event happens, instead of the second system checking repeatedly.
- What is automated data processing?
- Automated data processing is the use of software to collect, check, transform and output data with little manual handling, so records such as invoices, forms or payroll figures move through fixed steps to a finished result.
- Workflow
- A workflow is a defined sequence of steps, with a starting event and an end result, that moves work or information from one person or system to the next.