---
title: "Glossary: Discovery for agents"
type: "glossary-category"
canonical_url: "https://www.graphcanon.com/glossary/discovery-for-agents"
---

# Discovery for agents

_The machine-readable surfaces that let AI agents read GraphCanon as data, not scraped HTML._

Key concepts: llms.txt, Markdown twins, Structured data, GEO

## ai-catalog.json

ai-catalog.json is a well-known JSON manifest that advertises a site's agent-facing surfaces - its API, dataset, and MCP endpoint - in one discoverable place.

[Read more](/glossary/discovery-for-agents/ai-catalog.md)

## Generative engine optimization (GEO)

GEO is optimizing content so AI answer engines cite it accurately - the AI-era companion to SEO, focused on being quotable and verifiable, not just ranked.

[Read more](/glossary/discovery-for-agents/generative-engine-optimization.md)

## llms.txt

llms.txt is a plain-text file at a site's root that gives AI crawlers a curated, compact map of the most useful pages - like robots.txt, but for LLMs.

[Read more](/glossary/discovery-for-agents/llms-txt.md)

## Markdown twin

A markdown twin is a clean markdown version of an HTML page, served at the same path plus .md, so agents can read the content without parsing the page.

[Read more](/glossary/discovery-for-agents/markdown-twin.md)

## Sitemap

A sitemap is an XML file listing a site's canonical URLs so crawlers can discover every page, including ones that are hard to reach by following links.

[Read more](/glossary/discovery-for-agents/sitemap.md)

## Structured data (JSON-LD)

Structured data is machine-readable markup (usually JSON-LD following schema.org) embedded in a page so search engines and agents understand what it contains.

[Read more](/glossary/discovery-for-agents/structured-data.md)

[All glossary terms](/glossary.md)

---

**Machine-readable endpoints**

- JSON: [`/api/graphcanon`](/api/graphcanon)
- LLM index: [/llms.txt](/llms.txt)
- Full corpus: [/llms-full.txt](/llms-full.txt)

_GraphCanon - The knowledge graph for AI development. https://www.graphcanon.com/_