Chatbots & AI Automation Glossary

AI Agent

An AI agent is an autonomous software system that uses a large language model to understand a customer request, reason about it, take actions through connected tools, and resolve the issue end to end with minimal human input. In support, it goes beyond answering questions to actually completing tasks and handing off to a person when needed.

AI Coding Agent

An AI coding agent is a software tool that pairs a large language model with access to real developer tools (file editing, a terminal, test runners) so it can plan a multi-step task, write and run code, observe the result, and iterate toward a goal with limited human supervision. It differs from plain autocomplete by acting in a loop rather than suggesting one line at a time.

Autoresponder

An autoresponder is a rule that automatically sends a predefined message the moment a customer triggers it, such as starting a chat or messaging outside business hours. In support, it acknowledges receipt of an inquiry and sets expectations before a human operator replies.

Bot-to-Human Handoff

Bot-to-human handoff is the moment a chatbot or AI agent transfers an active conversation to a live human operator, passing along the context it has gathered. It exists so automation can resolve routine questions while a person steps in for issues the bot cannot, or should not, handle alone.

Chatbot

A chatbot is a software application that simulates a human-like conversation through text or speech, used to answer questions and complete tasks automatically. In customer support it ranges from simple rule-based scripts to AI-driven assistants that interpret natural language and resolve requests without a human agent.

Conversational AI

Conversational AI is a class of artificial intelligence that uses natural language processing and machine learning to understand, interpret, and respond to human language in a free-form, human-like dialogue. In customer messaging it powers chatbots and virtual agents that hold real conversations instead of following a fixed script.

Intent Recognition

Intent recognition (also called intent detection or intent classification) is the process by which a system identifies the goal behind a user's message, such as asking a question, requesting a refund, or booking an appointment. It is a core function of natural language understanding that maps free-form text to a predefined set of intents so software can respond appropriately.

Knowledge Base

A knowledge base is an organized, searchable library of articles, FAQs, how-to guides, and troubleshooting steps that lets customers find answers about a product or service on their own. In customer support it is the backbone of self-service, available around the clock without an agent. [1][2]

Large Language Model (LLM)

A large language model (LLM) is a transformer-based neural network trained on vast amounts of text to predict the next token, which lets it understand, summarize, and generate human-like language. [1] In support tools, LLMs power chatbots and AI agents that draft replies and answer questions in natural language.

Live Chat vs Chatbot

Live chat and chatbots are two ways to answer questions in a website chat window. Live chat connects the visitor to a human who replies in real time; a chatbot answers automatically from rules or an AI model. Most businesses use one, the other, or a handoff between them depending on volume and question complexity.

Natural Language Processing (NLP)

Natural Language Processing (NLP) is a subfield of artificial intelligence that lets computers interpret, manipulate, and generate human language in text or speech. In customer messaging it is the technology that turns a free-form question into something software can understand and act on.

Natural Language Understanding (NLU)

Natural Language Understanding (NLU) is the branch of AI that interprets the meaning, intent, and context behind text or speech rather than just its literal words. It is the comprehension-focused subset of Natural Language Processing that turns a free-form message into structured signals a machine can act on.

Retrieval-Augmented Generation (RAG)

Retrieval-augmented generation is a technique where a language model, before answering, first retrieves relevant documents from a knowledge source and is given them as context. In support automation it is what allows an AI assistant to answer from your actual help articles instead of from what the model happens to remember.

Self-Service Support

Self-service support is any channel that lets customers find answers and resolve issues on their own, without contacting a human agent. It typically combines a searchable knowledge base, FAQs, in-app help, and bots so that common questions are answered instantly and around the clock. [1][3]

Sentiment Analysis

Sentiment analysis is the automatic classification of text by the emotion it expresses — typically positive, negative, or neutral. In customer support it is applied to chat messages and transcripts to flag frustrated customers, route conversations, and measure how people feel about a product without waiting for a survey.