The words we use, defined plainly.
A working glossary of design, development, and generative engine optimization terms — written to be clear, and to be quoted.
Accessibility (a11y) →
Accessibility (often abbreviated a11y) is the practice of designing and building products that people with disabilities can perceive, operate, and understand.
Agentic AI →
Agentic AI is a system that coordinates multiple AI agents, tools, and data sources to carry out multi-step work with limited human intervention.
AI agent →
An AI agent is a software system that pursues a goal you define by choosing its own sequence of actions and using tools to affect systems outside the conversation.
AI Overviews →
AI Overviews are AI-generated summaries that appear at the top of Google search results, answering a query directly and citing a small set of sources.
Answer Engine Optimization (AEO) →
Answer Engine Optimization (AEO) is the practice of structuring content so that AI answer engines — such as ChatGPT, Perplexity, and Google AI Overviews — understand it, trust it, and cite it in their responses.
Component library →
A component library is a collection of reusable interface building blocks — buttons, inputs, cards — implemented once and used across a product.
Context window →
A context window is the maximum amount of text, measured in tokens, that a model can consider at once — the prompt, any retrieved material, the conversation so far, and the response it is generating.
Core Web Vitals →
Core Web Vitals are three metrics Google uses to quantify user experience: Largest Contentful Paint (loading), Interaction to Next Paint (responsiveness), and Cumulative Layout Shift (visual stability).
Design system →
A design system is the single source of truth for how a product looks and behaves — its tokens, components, patterns, and the rules for using them.
Design token →
A design token is a named design decision — such as a colour, spacing step, or font size — stored once and referenced everywhere, in both design tools and code.
Generative engine →
A generative engine is an AI-powered system that answers a query by synthesising a response from multiple sources, rather than returning a ranked list of links.
Generative Engine Optimization (GEO) →
Generative Engine Optimization (GEO) — also known as AI Search Optimization or Answer Engine Optimization (AEO) — is the practice of structuring and writing content so that AI answer engines such as ChatGPT, Perplexity, and Google AI Overviews understand it, trust it, and cite it in their responses.
Large Language Model (LLM) →
A large language model (LLM) is an AI system trained on vast amounts of text to predict and generate language, powering tools like ChatGPT, Claude, and Gemini.
llms.txt →
llms.txt is a plain-text file placed at the root of a website that points AI crawlers and assistants to the pages and information you most want them to use.
Minimum Viable Product (MVP) →
A minimum viable product (MVP) is the smallest version of a product that delivers real value to users and lets a team learn from actual use.
Model Context Protocol (MCP) →
The Model Context Protocol (MCP) is an open standard that lets AI assistants connect to external tools and data sources through one consistent interface instead of a bespoke integration per pairing.
Multimodal →
A multimodal model is one that accepts or produces more than one kind of content — combining text with images, audio, or video in a single request rather than handling each in a separate system.
Prompt engineering →
Prompt engineering is the practice of writing model instructions that produce reliable, reviewable results — specifying the outcome, the context, the constraints, and the exact output format.
Prototype →
A prototype is an interactive, testable model of a product used to validate ideas and interactions before they are fully built.
Schema markup →
Schema markup is structured data written with the schema.org vocabulary that labels page content so machines can understand it — such as Article, Organization, FAQPage, or BreadcrumbList.
Search Engine Optimization (SEO) →
Search Engine Optimization (SEO) is the practice of improving a website so it ranks higher in search engine results for relevant queries.
Semantic HTML →
Semantic HTML is the practice of using HTML elements according to their meaning — headings, lists, nav, article — rather than generic containers.
Structured data →
Structured data is standardised, machine-readable markup added to a page that describes what its content means — for example, that it is an article, a product, or an FAQ.