AI Glossary · 60 terms · Plain English
The AI glossary that actually explains things.
60 AI terms — LLM, RAG, fine-tuning, agents, embeddings, prompt engineering, and more — explained in plain English. Each entry links to a full guide on the site so you can go deeper without getting buried in jargon.
Core Concepts
Agentic AI
AI systems designed to take autonomous, multi-step action toward a goal.
Read definitionAGI (Artificial General Intelligence)
A hypothetical AI that matches or exceeds human cognitive ability across all tasks.
Read definitionAI Agent
An AI that takes actions in the world, not just generates text.
Read definitionAI Alignment
The problem of making AI systems do what humans actually want, safely.
Read definitionAI Sandbox
An isolated computing environment where AI agents can act without touching your real data or files.
Read definitionContext Window
The amount of text an AI can consider at once — its short-term memory.
Read definitionFrontier Model
The most capable AI models at the cutting edge — GPT-5.6, Claude Opus 4.8, Gemini 3.5 Pro.
Read definitionHallucination
When an AI confidently generates text that is plausible-sounding but factually wrong.
Read definitionLarge Language Model (LLM)
An AI trained on enormous amounts of text to predict what word comes next.
Read definitionLong Context
AI models that can hold millions of tokens at once — entire codebases, books, year-long threads.
Read definitionMultimodal AI
AI that handles text, images, audio, and video in a single model.
Read definitionOn-Device AI
AI that runs entirely on your phone or laptop — no cloud, no internet required.
Read definitionTokens
The chunks of text AI models read and produce — usually 3–4 characters each.
Read definitionModels & Architectures
Claude Opus
Anthropic's most capable model family — leads on coding and long-form reasoning.
Read definitionDiffusion Model
The AI architecture behind Stable Diffusion, DALL-E, Sora 2, and most modern image/video generators.
Read definitionGemini
Google's frontier AI family — biggest context window, strongest on multimodal.
Read definitionGPT-5
OpenAI's flagship model — reasoning, multimodal, and the model behind most ChatGPT Plus output.
Read definitionGrok
xAI's chatbot — real-time X access, fewer content restrictions, competitive with GPT-5.
Read definitionMixture of Depths (MoD)
A neural architecture where the model decides per-token how many layers to use — saving compute on easy tokens.
Read definitionMixture of Experts (MoE)
An AI architecture where only a fraction of the model "wakes up" per request.
Read definitionReasoning Model
An AI that "thinks" before answering — explicit step-by-step reasoning at inference time.
Read definitionTechniques & Methods
AI Detector
A tool that estimates how likely a piece of text was written by AI.
Read definitionAI Eval
Systematic tests that measure whether an AI model or app produces good output.
Read definitionAI Humanizer
A tool that rewrites AI-generated text to sound like a real person wrote it.
Read definitionAI Voice Cloning
AI that recreates a specific human voice from a short audio sample.
Read definitionBackground Coding Agent
An AI coding agent that works asynchronously in the cloud — assign a task, get a PR hours later.
Read definitionChain-of-Thought (CoT)
Prompting an AI to "show its work" — dramatically improves accuracy on hard problems.
Read definitionComputer Use
AI that can see your screen, move your cursor, and click — controlling a computer like a person would.
Read definitionEmbeddings
How AI represents meaning as lists of numbers — the math behind search and RAG.
Read definitionFine-Tuning
Continuing to train a pre-trained AI model on your own specific data.
Read definitionFunction Calling
How LLMs invoke tools — the model outputs structured JSON instead of free text.
Read definitionModel Context Protocol (MCP)
The open standard that lets AI assistants connect to external tools and data sources.
Read definitionModel Distillation
Training a small AI model to mimic a larger one — how GPT-5 mini came from GPT-5.
Read definitionPrompt Caching
A pricing trick that cuts AI API input cost by 50–90% for repeat-context workflows.
Read definitionPrompt Engineering
The skill of writing clear, structured instructions that get the best results from AI.
Read definitionRAG (Retrieval Augmented Generation)
The technique that lets AI actually know things it was not trained on.
Read definitionRAG vs Fine-Tuning
When to use RAG (retrieval) versus fine-tuning (continued training) — the central architectural choice.
Read definitionRLHF (Reinforcement Learning from Human Feedback)
How AI labs teach models to be helpful, harmless, and honest — using human ratings.
Read definitionSpeculative Decoding
A trick that makes frontier AI 2-3x faster by using a tiny model to guess tokens for a big one to verify.
Read definitionTemperature
The AI setting that controls how creative (high) or predictable (low) responses are.
Read definitionTest-Time Compute
Letting an AI think longer at inference time — the breakthrough behind reasoning models.
Read definitionTool Use
How AI models call external tools — search, code execution, APIs — to do real work.
Read definitionTools & Platforms
AI Search
Search engines that synthesise answers from sources rather than returning a list of links.
Read definitionChatGPT
OpenAI's flagship AI assistant — the app that kicked off the AI boom in late 2022.
Read definitionClaude
Anthropic's AI assistant — known for writing quality, long-document analysis, and coding.
Read definitionCursor
The AI-first VS Code fork — most-used AI coding tool among professional developers.
Read definitionDevin
Cognition's autonomous AI software engineer — takes a Jira ticket, opens a PR.
Read definitionElevenLabs
The leading AI voice generator — natural-sounding voices, cloning, multilingual.
Read definitionGitHub Copilot
The AI coding autocomplete that started the AI-pair-programming category.
Read definitionHugging Face
The GitHub of AI — hosts open-source models, datasets, and inference for the whole community.
Read definitionMidjourney
The AI image generator with the most distinctive aesthetic — runs in Discord.
Read definitionNotebookLM
Google's research notebook — upload sources, get a personalised AI tutor with citations.
Read definitionOpen Source AI
AI models whose weights are publicly released — anyone can run, fine-tune, and modify them.
Read definitionPerplexity
The AI search engine — answers with citations, replaces Google for research queries.
Read definitionSora 2
OpenAI's AI video generator — text or image to high-quality video clips.
Read definitionStable Diffusion
The open-source AI image generator — runs locally, infinitely customisable.
Read definitionVector Database
A database optimised for storing and searching AI embeddings — the backbone of every RAG system.
Read definitionAI in Business
AI Startup
A company building on or with AI — the largest startup category of 2024–2026.
Read definitionAPI (Application Programming Interface)
How developers access AI models programmatically — the foundation of every AI product.
Read definitionSovereign AI
AI models built and hosted within a country's borders for data sovereignty and strategic independence.
Read definition