The language of AI-era websites.

AI crawler

An AI crawler is an automated bot that fetches web pages to feed AI systems — training data for models or live answers in tools like ChatGPT and Perplexity. Examples: GPTBot, ClaudeBot, PerplexityBot.

Read definition →

AI Overviews

AI Overviews are Google's AI-generated answer summaries that appear at the top of search results, pulling and citing content from multiple web pages to answer a query before the classic blue links.

Read definition →

Answer Engine Optimization (AEO)

Answer Engine Optimization (AEO) is the practice of structuring web content so answer engines like ChatGPT, Perplexity, and Google AI Overviews can extract, trust, and cite it directly in their answers.

Read definition →

Featured snippet

A featured snippet is the boxed answer Google shows at the top of search results, pulled from a ranking page to answer a query directly. It appears as a paragraph, list, or table with a link to the source.

Read definition →

Generative Engine Optimization (GEO)

Generative Engine Optimization (GEO) is the practice of shaping a website's content, structure, and signals so AI engines like ChatGPT, Perplexity, and Google's AI Overviews cite it when generating answers.

Read definition →

llms.txt

llms.txt is a plain-text file at a site's root that gives AI models a curated, Markdown-linked map of your most important pages, so they can find and cite your content more reliably.

Read definition →

Agentic workflow

An agentic workflow is a multi-step process where one or more AI agents plan, act, use tools, and check their own results in a loop — often split across specialized subagents — to complete a larger task.

Read definition →

AI agent

An AI agent is a system built on a large language model that pursues a goal across multiple steps — deciding actions, using tools, and reacting to results — rather than answering a single prompt in one shot.

Read definition →

AI-assisted web development

AI-assisted web development is building and maintaining websites with AI agents doing the heavy lifting under human direction — generating, editing, and testing real code — rather than a developer typing every line or a no-code tool producing a fixed template.

Read definition →

Claude Code

Claude Code is Anthropic's terminal-based AI coding agent: it reads your repository, runs commands, edits files, and verifies its own work in a loop — acting on a real codebase rather than handing you snippets to paste.

Read definition →

Coding agent

A coding agent is an AI system that performs software tasks end to end — reading code, running commands, editing files, and checking results in a loop — instead of only suggesting code for a human to copy.

Read definition →

Context window

A context window is the amount of text — measured in tokens — a large language model can consider at once. Everything the model 'sees' for a task, including instructions, code, and history, must fit inside it.

Read definition →

Human-in-the-loop

Human-in-the-loop is a workflow where a person reviews and approves an AI system's output before it takes effect, keeping a human accountable for every consequential decision the AI proposes.

Read definition →

Model Context Protocol (MCP)

The Model Context Protocol (MCP) is an open standard that lets AI agents connect to external tools and data sources — like analytics, a database, or a browser — through a consistent interface, so the model reasons over real data instead of guesses.

Read definition →

Spec-driven development

Spec-driven development is an AI coding practice where you write and approve a short specification before any code is generated, so the artifact you review is the plan — not a large diff after the fact.

Read definition →

Vibe coding

Vibe coding is building software by prompting an AI in a loose, conversational way and accepting what it produces without a written spec — fast for prototypes, risky for production code you have to maintain.

Read definition →

301 redirect

A 301 redirect is a server response that permanently sends a browser and search engines from an old URL to a new one. It passes nearly all ranking signals and is the standard way to move content without losing SEO.

Read definition →

Canonical URL

A canonical URL is the version of a page you tell search engines is the 'real' one when several URLs show the same or near-identical content, so ranking signals point to one address instead of being split.

Read definition →

Crawl budget

Crawl budget is the number of pages a search engine like Google will crawl on your site within a given window. It is set by how fast your server responds and how much the crawler wants your URLs.

Read definition →

DNS cutover

DNS cutover is the moment you change a domain's DNS records to point traffic from an old server to a new one. It's the final switch that makes a migration go live.

Read definition →

Index bloat

Index bloat is when a search engine indexes far more pages from your site than have real value — thin, duplicate, or low-quality URLs — which dilutes crawl attention and weakens how the site ranks overall.

Read definition →

Redirect map

A redirect map is a spreadsheet or file that pairs every old URL with its new destination, so a site migration sends each old page and its SEO value to the right new page.

Read definition →

WordPress to Next.js migration

WordPress to Next.js migration is the process of moving a site off WordPress and rebuilding it in Next.js, while preserving URLs, content, and search rankings through 301 redirects and matching metadata.

Read definition →