All terms
Agentic / AI
llms.txt
llms.txt is a proposed web standard: a Markdown file placed at the root of a website (/llms.txt) that provides large language models with a concise, curated overview of the site's most important content and links, helping AI systems find and use the right information.
Also known asllms.txt filellms-full.txt
In depth
What llms.txt means.
llms.txt is a proposal, introduced in 2024, for a standard file that helps large language models consume a website. It is a Markdown document served at the site root - /llms.txt - that summarizes what the site is and points to its most important pages, often with short descriptions. The idea is that an LLM, which works with limited context and benefits from clean text, can read this curated map instead of crawling and guessing at a site's structure.
The format is deliberately simple and human-readable: a title, a short summary, and lists of links grouped into sections. A companion convention, llms-full.txt, provides a single expanded file containing the actual content, so a model can ingest a site's documentation in one fetch rather than following many links.
llms.txt is distinct from robots.txt and sitemap.xml. robots.txt tells crawlers what they may access; sitemap.xml lists URLs for search indexing; llms.txt curates and explains content specifically for language models at inference or ingestion time. It is an emerging convention rather than a formally ratified standard, and adoption is voluntary.
How biz collect relates
llms.txt in biz collect.
biz collect genuinely ships both files: it serves /llms.txt as a concise, curated map of the product, docs, and key pages, and /llms-full.txt as an expanded single document. This is part of its agent-first positioning - making the product easy for an AI system to understand and integrate, not just for human readers.
Combined with an OpenAPI 3.1 specification, a stable JSON schema, and predictable endpoints, the llms.txt files help an LLM or agent learn how to call biz collect correctly. The goal is that a model can go from discovering the product to making a valid /v1/search request with minimal guesswork.
Go deeper
Where this concept shows up across biz collect:
llms.txt
Frequently asked questions.
How is llms.txt different from robots.txt?
robots.txt instructs crawlers on what they are allowed to access. llms.txt instead curates and summarizes a site's key content for large language models. They serve different audiences and purposes and can coexist.
What is llms-full.txt?
llms-full.txt is a companion convention to llms.txt that contains a site's important content expanded into a single file, so a language model can ingest it in one fetch rather than following many separate links.
Still have questions? Talk to us.
Turn the concept into real data.
Sign up free with 200 signup credits, no credit card. POST a city plus keywords and get an enriched, structured list of businesses back as JSON.
No credit card required200 signup credits20 daily login credits