Glossary
AI customer service glossary
The terms behind AI agents and conversational commerce, explained without jargon, with concrete examples.
28 terms
Start here
Fundamentals
AI technology
Fundamentals
AI technology
All terms from A to Z
A
- Fundamentals
AI agent
An AI agent is software that uses a large language model to pursue a goal on someone's behalf: it understands a request, decides which steps to take, calls tools such as a search engine or an API to act, and checks the result before answering.
- Fundamentals
AI chatbot vs AI agent
An AI chatbot uses a language model to answer messages, while an AI agent also decides which steps to take and uses tools to act on the user's behalf. Those tools can be search, APIs or business systems.
- AI technology
AI guardrails
AI guardrails are the technical and policy controls that keep an AI system within the limits its operators intend. They define what it covers, what data it sees, what actions it can take and what it must refuse.
- AI technology
AI hallucination (LLM hallucination)
An AI hallucination is an answer from a language model that sounds fluent and confident but is false, invented or not supported by its sources. In customer service, it typically shows up as a wrong price, policy or delay.
- Fundamentals
AI workflow automation
AI workflow automation runs predefined sequences of triggers, conditions and actions across business tools, with some steps performed by an AI model. Typical AI steps classify a message, extract data or draft a reply.
C
- Fundamentals
Chatbot
A chatbot is a computer program that holds a conversation with people in natural language, by text or voice, to answer questions or complete simple tasks. Modern chatbots range from scripted decision trees to assistants built on large language models.
- Fundamentals
Conversational AI
Conversational AI is the set of technologies that let software understand people and reply to them in natural language, by text or voice. Language understanding, dialogue management and text or speech generation are its building blocks; chatbots, voice assistants and AI agents are its applications.
- Channels and commerce
Conversational commerce
Conversational commerce is buying and selling through conversations, where customers get advice, find products and resolve questions by talking with a person or an AI assistant. It happens on website chat, messaging apps or voice.
- Customer service and metrics
CSAT (customer satisfaction score)
CSAT (customer satisfaction score) is a metric of how satisfied customers are with a specific interaction, product or service. It usually comes from a one-question survey answered on a 1-to-5 scale.
- Customer service and metrics
Customer self-service
Customer self-service is any way for customers to find answers or complete tasks on their own, without waiting for a member of staff. Help centres, FAQs, order-tracking pages and AI assistants are common forms.
D
- Customer service and metrics
Deflection rate (ticket deflection)
Deflection rate is the share of customer requests resolved through self-service — a help centre, FAQ or AI assistant — without a support agent having to handle them.
E
- AI technology
Embeddings
An embedding is a list of numbers (a vector) that represents the meaning of a text, image or other item, so that similar items get nearby vectors. Embeddings are what makes search by meaning possible.
- Compliance
EU AI Act (chatbot transparency)
The EU AI Act (Regulation (EU) 2024/1689) is the European Union's law on artificial intelligence. For chatbots, its key rule is that people must be told they are interacting with an AI system.
F
- Customer service and metrics
First response time (FRT)
First response time (FRT) is the time between a customer's first message and the first reply from the business. It is usually reported as an average or median per channel and period.
G
- Compliance
GDPR and AI chatbots
An AI chatbot that talks with people in the EU processes personal data, so the business running it must apply the General Data Protection Regulation (GDPR) to its conversations. That data includes names, emails, order details and whatever users type.
H
- Customer service and metrics
Human handoff
Human handoff is the moment an AI assistant or chatbot passes a conversation, with its context, to a human agent. It happens when a request needs a person or the customer asks for one.
I
- AI technology
Intent detection
Intent detection is the task of identifying what a person wants to achieve from what they write or say, so that a system can respond or route the request. Typical intents are tracking an order, requesting a refund or asking about a product.
K
- Fundamentals
Knowledge base
A knowledge base is an organised, searchable collection of information about a product, service or organisation, used by customers, support teams and AI assistants to find answers. It typically holds FAQs, guides, policies and procedures.
L
- AI technology
Large language model (LLM)
A large language model (LLM) is a neural network trained on very large amounts of text to predict the next word, which lets it understand and generate natural language. It is the reasoning engine behind modern chatbots and AI agents.
M
- AI technology
MCP (Model Context Protocol)
The Model Context Protocol (MCP) is an open standard that defines how AI applications connect to external tools and data sources. Any compatible assistant can then use any compatible service without a custom integration.
- Customer service and metrics
Multilingual customer support
Multilingual customer support means helping customers in their own language — on chat, email, messaging or phone — whatever language the support team itself works in.
O
- Customer service and metrics
Omnichannel customer service
Omnichannel customer service means helping customers on every channel they use, with history and context shared across those channels so they never have to start over. Typical channels are website chat, email, WhatsApp, social messaging and phone.
- Channels and commerce
Order tracking automation (WISMO)
Order tracking automation answers “where is my order?” questions, often called WISMO, automatically. It reads the order's status and shipment tracking from the store and carrier systems instead of involving an agent.
P
- Channels and commerce
Product recommendation engine
A product recommendation engine is software that suggests the products a shopper is most likely to want. It relies on their behaviour, product attributes, what similar shoppers bought or what they ask for in a conversation.
- AI technology
Prompt engineering
Prompt engineering is the practice of designing the instructions, context and examples given to a language model so that it produces reliable, useful outputs. For a support assistant, the core prompt sets its role, rules and tone.
R
- AI technology
Retrieval-augmented generation (RAG)
Retrieval-augmented generation (RAG) is a technique in which an AI system first retrieves relevant passages from a trusted source, such as a knowledge base or a product catalog, then gives them to a language model so that its answer rests on those passages rather than on its memory alone.
V
- AI technology
Vector search (semantic search)
Vector search is a retrieval method that returns the items whose embeddings are closest to the query's embedding, so results match by meaning rather than by shared keywords. It is the usual engine of semantic search.
W
- Channels and commerce
WhatsApp Business API (Cloud API)
The WhatsApp Business API lets businesses send and receive WhatsApp messages from software such as a CRM, a shared inbox or an AI assistant. Today it is the WhatsApp Business Platform's Cloud API, hosted by Meta.
Explore by theme
Fundamentals
AI technology
Customer service and metrics
Channels and commerce
Ready in 5 minutes
Try it on your own questions.Your agent can be live today.
Connect your store or website, let the agent learn from it, and test it before you choose a plan. No credit card required.
No credit card
Cancel anytime
GDPR-native · EU hosting