This AI glossary explains the key terms — LLM, prompt, token, RAG, agent, hallucination and more — in plain English. Knowing the vocabulary helps you use AI more confidently.
Core concepts
AI — software doing tasks associated with human intelligence. Machine learning — systems that learn patterns from data. Deep learning — machine learning using many-layered neural networks. Neural network — a brain-inspired system of connected nodes. Model — the trained system at the heart of an AI tool. Generative AI — AI that creates new content.
Language-model terms
LLM — large language model, the AI behind chatbots. Prompt — the instruction you give an AI. Prompt engineering — crafting effective prompts. Token — a chunk of text a model processes. Context window — how much text a model can consider at once. Fine-tuning — adapting a model to a specific task. Parameters — the model’s learned settings.
Behaviour and applications
Hallucination — when AI confidently states something false. RAG — retrieval-augmented generation, grounding answers in retrieved documents. AI agent — AI that plans and carries out multi-step tasks. Multimodal — handling text, images, audio and video. Open-weight — a downloadable, self-hostable model. Inference — running a trained model to get output. Training — teaching a model from data. Bias — skew learned from training data. AI can fabricate facts, figures and citations with total confidence (a “hallucination”). Treat AI output as a draft and verify anything important against a reliable source — this matters most for medical, legal, financial and academic use.
If you find yourself juggling a separate subscription for chat, automation, transcription and image generation, one option worth knowing is a single platform that runs them together — osFoundry is one such agentic AI platform that consolidates chat, agents and internal apps in one workspace, with a bring-your-own-key model so you choose the underlying AI.
Related reading
This article is general information, not professional, legal or financial advice. AI tools, prices and availability change fast — verify current details on the official source before you rely on them.