GEO and AI visibility · Madrid

llms.txt specification in Madrid

The robots.txt of the AI era. Adoption is still under 5%. Madrid operators face the same llms.txt specification discipline as global peers, with local context (timezone, channel mix, buying patterns) shifting which moves carry the most leverage.

Apply for a free audit →Full llms.txt specification reference →

Definition

What is llms.txt specification?

llms.txt is a proposed plain-text manifest at /llms.txt that summarizes a website's content for large language model crawlers. The spec, hosted at llmstxt.org, defines a Markdown structure with sections of named links so models can ingest a curated map of the site. In the Q1 2026 tracked corpus, adoption was approximately 4% across the analyzed cohort.

How it lands in Madrid

The Madrid angle

Xpand Media runs llms.txt specification inside Madrid-based engagements with the local context built in: Europe/Madrid timezone, market-specific buyer behavior, and the platforms Spain-based operators actually use. The discipline is global; the operational rhythm is local.

Services that operate llms.txt specification

Where llms.txt specification sits in our work

Madrid · service

Get Your Brand Recommended by AI

Optimize your brand to appear in AI-generated recommendations across ChatGPT, Gemini, Perplexity, and Google AI Overviews.

FAQ

llms.txt specification questions from Madrid operators

Where does llms.txt live?
At the site root, at the path /llms.txt, served as text/plain. Following the spec, it uses Markdown structure with H1 (site name), blockquote summary, and named sections with link lists.
How is it different from robots.txt?
robots.txt controls crawler access. llms.txt curates content discovery — it tells the model what's worth reading, not whether it can read.
Do AI engines actually use llms.txt?
Adoption is partial. Anthropic publicly references it. OpenAI and Google have not confirmed dedicated parsers but treat it as crawlable plain text. Adding it is low cost and forward-compatible.
Should we also publish llms-full.txt?
Yes if the site has high-volume content. llms-full.txt is the long-form variant that concatenates page content, intended for offline LLM ingestion.
What format do links need to be in?
Standard Markdown: hyphen, space, bracketed link text, parenthesized URL, optional colon-prefixed description. Other formats (em-dash separated, plain URL lists) may fail spec parsers.

Run llms.txt specification in Madrid

Talk to the team running llms.txt specification engagements in Madrid.

Apply for a free audit →Read the State of GEO 2026 →

Spinning up

llms.txt specification in Madrid

What is llms.txt specification?

llms.txt specification questions from Madrid operators

Where does llms.txt live?

At the site root, at the path /llms.txt, served as text/plain. Following the spec, it uses Markdown structure with H1 (site name), blockquote summary, and named sections with link lists.

How is it different from robots.txt?

robots.txt controls crawler access. llms.txt curates content discovery — it tells the model what's worth reading, not whether it can read.

Do AI engines actually use llms.txt?

Adoption is partial. Anthropic publicly references it. OpenAI and Google have not confirmed dedicated parsers but treat it as crawlable plain text. Adding it is low cost and forward-compatible.

Should we also publish llms-full.txt?

Yes if the site has high-volume content. llms-full.txt is the long-form variant that concatenates page content, intended for offline LLM ingestion.

What format do links need to be in?

Standard Markdown: hyphen, space, bracketed link text, parenthesized URL, optional colon-prefixed description. Other formats (em-dash separated, plain URL lists) may fail spec parsers.