AI crawler
An AI crawler is a bot, such as GPTBot, ClaudeBot, or PerplexityBot, that fetches web content to train language models or to retrieve sources for AI-generated answers.
Documentation AI glossary.
Answer engine
An answer engine is a system that responds to a question with a direct, synthesized answer instead of a list of links; ChatGPT, Perplexity, and Google AI Overviews are examples.
Answer-first writing
Answer-first writing is a documentation style that states the direct answer in the first sentence of a page or section, before any background or context.
Chunking
Chunking is the process of splitting documentation into small, self-contained passages before indexing, so a retrieval system can find and return the exact section that answers a question.
Content gap
A content gap is a question users ask that your documentation does not answer, often discovered through unanswered chatbot queries or failed searches.
Deflection rate
Deflection rate is the percentage of user questions resolved by self-service, such as a docs AI chatbot, that would otherwise have become support tickets.
Docs-as-code
Docs-as-code is an approach that treats documentation like software: written in plain text, stored in version control, reviewed in pull requests, and published through CI pipelines.
Embedding
An embedding is a numeric vector that captures the meaning of a piece of text, letting a docs search system match questions to relevant passages by semantic similarity rather than keywords.
Federated search
Federated search is a single search experience that queries content living in multiple separate systems and returns one combined set of results.
GEO (Generative Engine Optimization)
Generative Engine Optimization (GEO) is the practice of structuring content so AI answer engines like ChatGPT, Perplexity, and Google AI Overviews cite it in their responses.
Grounding
Grounding gives an AI model trusted source material and instructs it to base its answer on that evidence. It reduces unsupported claims but does not eliminate model error.
Hallucination
A hallucination is a confident but false statement produced by an AI model, such as a chatbot inventing a configuration option that does not exist in the documentation.
llms.txt
llms.txt is a proposed standard file, served at a site's root, that gives large language models a curated markdown index of the site's most important pages.
MCP (Model Context Protocol)
The Model Context Protocol (MCP) is an open standard that lets AI assistants such as Claude connect to external tools and data sources, including documentation, through a common server interface.
RAG (retrieval-augmented generation)
Retrieval-augmented generation (RAG) is a technique where an AI model retrieves relevant passages from a knowledge base, such as product documentation, and uses them to generate a grounded answer.
Ticket deflection
Ticket deflection is the practice of resolving user questions through self-service resources, such as documentation or an AI assistant, before they become support tickets.