Core concepts
Chatbot
A program that simulates conversation with users — increasingly powered by LLMs to handle natural-language questions and tasks.
01 ——
In plain English
A chatbot is software that conducts a conversation, usually through text or voice. Old-school chatbots followed rigid scripts and decision trees; modern AI chatbots use LLMs and can handle open-ended questions.
Common uses:
- Customer support — answering FAQs, escalating to humans
- Sales / lead qualification — chatting with site visitors
- Internal helpdesks — IT, HR, knowledge bases
- Consumer apps — companions, learning, entertainment
Chatbot vs AI assistant vs agent:
- Chatbot — typically reactive, answers questions
- AI assistant — broader capability, can use tools, has memory
- Agent — autonomous, can plan and take multi-step actions
Most AI chatbots today are powered by an LLM behind the scenes, often combined with RAG to ground answers in company-specific content.
02 ——
Related terms
AI Assistant
A conversational AI tool that helps users with tasks like writing, scheduling, research, or answering questions in natural language.
Agent
An AI system that can take actions, use tools, and make decisions autonomously to complete a goal.
Conversational AI
AI systems designed for natural back-and-forth dialogue with users — covering chatbots, voice assistants, and AI agents.
LLM
Large Language Model — the type of AI behind tools like ChatGPT and Claude, trained to understand and generate text.
RAG
Retrieval-Augmented Generation — a technique that gives an AI model access to external documents before it answers, so it can cite real, up-to-date sources.
Back to glossaryLast reviewed May 2026