— AI Glossary
Every AI term that matters, in plain English.
53 definitions across models, tools, techniques, and concepts — written for practitioners who want to understand AI deeply enough to ship with it.
A
Concepts
Academic AI
The research-led path: studying ML theory, model architecture, and pure science.
Concepts
AI Agent
An AI system that decides its own next action and takes multi-step actions autonomously.
Concepts
AI Automation
Wiring AI into multi-step workflows so they run without human intervention.
Concepts
AI Orchestration
Coordinating multiple AI calls, tools, and decisions into a single workflow.
Concepts
AI Search
Search engines that answer questions in natural language with citations.
Companies
Anthropic
The AI safety company that builds Claude.
Infrastructure
API
An interface for programs to call AI models or services programmatically.
Concepts
Applied AI
The practical use of AI tools to ship products and outcomes.
C
Techniques
Chain-of-Thought (CoT)
A prompting technique where you ask the AI to think step-by-step before answering.
Tools
ChatGPT
OpenAI's flagship AI chat product, the most-used LLM globally.
Tools
Claude
Anthropic's family of AI assistants — known for strong reasoning, long context, and code quality.
Infrastructure
Cloudflare
Edge platform with AI Workers — runs ML models close to your users globally.
Concepts
Context Window
The maximum text an LLM can read in one prompt.
Tools
Cursor
An AI-first code editor — VS Code fork with deep Claude/GPT integration.
F
G
Tools
Gemini
Google's AI assistant family, deeply integrated with Google Workspace.
Tools
GitHub Copilot
GitHub's AI pair-programmer — AI autocomplete inside any editor.
Concepts
Google AI Overviews
Google's AI-generated answers that appear at the top of search results.
Tools
Google AI Studio
Google's developer playground for testing Gemini and getting API keys.
Companies
Google DeepMind
Google's AI research arm — builds Gemini, AlphaFold, and more.
Tools
Groq
A high-speed AI inference provider — 10x faster than typical APIs.
L
Models
LLM (Large Language Model)
An AI model trained on huge amounts of text that can understand and generate human language.
Techniques
LoRA (Low-Rank Adaptation)
An efficient way to fine-tune large models by training only a small set of new parameters.
Tools
Lovable
AI app builder — opinionated full-stack apps with Supabase backend.
M
P
R
S
Techniques
Semantic Search
Search that understands meaning, not just keyword matches.
Concepts
SEO
Search Engine Optimisation — making pages findable on Google, Bing, AI Search.
Tools
Supabase
Open-source Firebase alternative — Postgres, Auth, Storage, Vector search in one.
Techniques
System Prompt
The hidden instruction that shapes an AI's persona, rules, and behaviour.
T
Concepts
Temperature
An LLM setting that controls how 'creative' vs 'focused' outputs are.
Concepts
Tokens
The chunks of text LLMs process — roughly 0.75 words each.
Concepts
Tool Use
An AI's ability to call external tools (APIs, code, search) instead of just generating text.
Techniques
Training Data
The text, images, or examples used to teach an AI model what to do.
Techniques
Tree-of-Thought (ToT)
An advanced reasoning technique where the AI explores multiple reasoning paths.
V
Tools
v0 by Vercel
AI UI generator — describe a component, get React + Tailwind code.
Tools
Vector Database
A database optimised for storing and searching embeddings by similarity.
Infrastructure
Vercel
The hosting platform for modern web apps — deploys in seconds.
Concepts
Vibe Coding
Building software by describing what you want in English while AI writes the code.