The Beginner Glossary of AI Terms
From conversational AI to tokens, this plain-language glossary explains the words you will see most often.
Every field has its jargon, and AI is no exception. Here are the words you will bump into most, each in one plain sentence. Keep this handy.
- AI (Artificial Intelligence): software that can do tasks we used to think needed a human, like writing or answering questions.
- Model: the actual trained AI “brain” that generates answers. GPT-5 and Claude are models.
- LLM (Large Language Model): the kind of AI behind chat tools, trained on huge amounts of text to predict words.
- Prompt: what you type in, your question or instructions.
- Token: a small chunk of text, roughly a word or piece of one, that the AI reads and counts.
- Context window: how much text the AI can keep in mind at once, its short-term memory.
- Hallucination: when AI states something false with total confidence.
- Training: the long process of teaching a model by having it read enormous amounts of data.
- Generative AI: AI that creates new things, text, images, audio, rather than just sorting or labeling.
- Chatbot: an AI you talk to in a back-and-forth conversation.
- Agent: an AI that can take actions and use tools, not just answer.
- Open source: AI whose inner workings are shared publicly for anyone to use or inspect.
You do not need to memorize these. Skim them once, and they will click into place the next time you see them in the wild. Curious about a word that is not here? Just ask an AI assistant to “explain it like I am five.”