{
  "path": "/agents",
  "title": "Agents",
  "description": "How AI agents and language models read poe2k.com: every standard and format the site follows for them, where each one is, and how to find it.",
  "data": {
    "kind": "agents",
    "markdown": "`<page>` is a page's own address and `<section>` a section's; each is shown with the address it makes for `/db/tools` and `/db`. Every address here is on https://poe2k.com.\n\n## Read the pages\n\nEvery page reads without JavaScript, and has the same content as Markdown and its facts as JSON-LD.\n\n### Markdown of every page\n\nA page's content without its navigation and scripts, opening with YAML front matter: title, description, url, the section of a page that has one and, for articles, updated.\n\n- Where: `<page>.md` ([`/db/tools.md`](https://poe2k.com/db/tools.md))\n- How to find it: `<link rel=\"alternate\" type=\"text/markdown\">` in the head.\n- Specification: [Per-page Markdown source endpoints](https://specification.website/spec/agent-readiness/markdown-source-endpoints/), convention\n\n### llms.txt\n\nWhat poe2k is, how to describe it, and an index of the sections; each section has its own scoped llms.txt.\n\n- Where: [`/llms.txt`](https://poe2k.com/llms.txt), `<section>/llms.txt` ([`/db/llms.txt`](https://poe2k.com/db/llms.txt))\n- How to find it: `Link: </llms.txt>; rel=\"describedby\"` on every response, and `<link rel=\"describedby\">` in every head, naming the section's own where there is one.\n- Specification: [The /llms.txt file (v2)](https://llmstxt.org/), convention\n\n### Structured data\n\nTyped facts about each page: a breadcrumb trail, and what the page is (a collection, a person's profile, a tool as a SoftwareApplication, an article).\n\n- Where: each page's head, as an application/ld+json script\n- How to find it: In the HTML before any script runs.\n- Specification: [schema.org in JSON-LD](https://schema.org/), standard\n\n### Schemamap\n\nEach page's JSON-LD graph on its own, and an index of them with their schema.org types.\n\n- Where: `<page>.jsonld` ([`/db/tools.jsonld`](https://poe2k.com/db/tools.jsonld)), [`/schemamap.xml`](https://poe2k.com/schemamap.xml)\n- How to find it: `<link rel=\"alternate\" type=\"application/ld+json\">` and `<link rel=\"schemamap\">` in the head; the API catalog, under a URI relation.\n- Specification: [Schemamap](https://specification.website/spec/agent-readiness/schemamap/), proposal\n\n## Find what exists\n\nEach of these answers \"what does this site offer\" from one fetch, without reading any page.\n\n### Link headers\n\nEvery response, an image's or a JSON file's too, links llms.txt, the API catalog, the sitemap, the feeds, the skills and the AI catalog; a Markdown file's links its section's llms.txt.\n\n- Where: every response\n- How to find it: `curl -sI https://poe2k.com/`\n- Specification: [RFC 8288: Web Linking](https://www.rfc-editor.org/rfc/rfc8288), standard\n\n### API catalog\n\nA linkset of every API and machine-readable resource, each with its description and documentation.\n\n- Where: [`/.well-known/api-catalog`](https://poe2k.com/.well-known/api-catalog)\n- How to find it: `Link: <…>; rel=\"api-catalog\"` on every response.\n- Specification: [RFC 9727: api-catalog](https://www.rfc-editor.org/rfc/rfc9727), standard\n\n### AI catalog\n\nThe Agent Skill, with its media type and example questions.\n\n- Where: [`/.well-known/ai-catalog.json`](https://poe2k.com/.well-known/ai-catalog.json)\n- How to find it: `Agentmap:` in robots.txt, `rel=\"ai-catalog\"` in the head and the `Link` header.\n- Specification: [Agentic Resource Discovery](https://specification.website/spec/agent-readiness/agentic-resource-discovery/), draft\n\n### Agent Skill\n\nA SKILL.md that teaches an agent when to use poe2k and how to read it; the index has its sha256 digest.\n\n- Where: [`/.well-known/agent-skills/index.json`](https://poe2k.com/.well-known/agent-skills/index.json), [`/.well-known/agent-skills/poe2k/SKILL.md`](https://poe2k.com/.well-known/agent-skills/poe2k/SKILL.md)\n- How to find it: `Link: <…>; rel=\"agent-skills\"` and the API catalog.\n- Specification: [Agent Skills Discovery (v0.2.0)](https://github.com/cloudflare/agent-skills-discovery-rfc), draft\n\n### Page index\n\nEvery page as JSON with its addresses, section, schema.org types, headings, update and token estimate.\n\n- Where: [`/agents/pages.json`](https://poe2k.com/agents/pages.json)\n- How to find it: The API catalog and the Agent Skill.\n- Specification: [poe2k's own: AgentPage, in the file itself](https://poe2k.com/agents/pages.json), convention\n\n### Sitemap\n\nEvery page search engines get, with its last change where the page knows it.\n\n- Where: [`/sitemap.xml`](https://poe2k.com/sitemap.xml)\n- How to find it: `Sitemap:` in robots.txt and the `Link` header.\n- Specification: [Sitemaps XML format](https://www.sitemaps.org/protocol.html), standard\n\n### AI Discovery Document\n\nThe news API's actions, for agents that read this draft.\n\n- Where: [`/.well-known/ai`](https://poe2k.com/.well-known/ai)\n- How to find it: The API catalog.\n- Specification: [draft-aiendpoint-ai-discovery-01](https://datatracker.ietf.org/doc/html/draft-aiendpoint-ai-discovery-01), draft\n\n## Feeds and APIs\n\nNews in the formats feed readers and agents already read.\n\n### RSS and JSON Feed\n\nEvery overlay release and every post, newest first, in full.\n\n- Where: [`/feed.xml`](https://poe2k.com/feed.xml), [`/feed.json`](https://poe2k.com/feed.json)\n- How to find it: `<link rel=\"alternate\">` in the head and the `Link` header.\n- Specification: [RSS 2.0 and JSON Feed 1.1](https://www.jsonfeed.org/version/1.1/), standard\n\n### News API\n\nEvery published article as JSON, and each one with its Markdown; read-only, no auth.\n\n- Where: [`/api/news/all.json`](https://poe2k.com/api/news/all.json), [`/api/news/openapi.json`](https://poe2k.com/api/news/openapi.json)\n- How to find it: The API catalog names the OpenAPI document as the API's `service-desc`.\n- Specification: [OpenAPI 3.1](https://spec.openapis.org/oas/v3.1.0), standard\n\n## What agents may do with it\n\npoe2k wants to be read, cited and learned from: every crawler may fetch everything, for search, live answers and training.\n\n### robots.txt, by name\n\nAllows everyone, and names the AI crawlers (GPTBot, ClaudeBot, PerplexityBot and others), so the policy is explicit.\n\n- Where: [`/robots.txt`](https://poe2k.com/robots.txt)\n- How to find it: At its fixed address.\n- Specification: [RFC 9309: Robots Exclusion Protocol](https://www.rfc-editor.org/rfc/rfc9309), standard\n\n### Content Signals\n\n`Content-Signal: search=yes, ai-input=yes, ai-train=yes` in each robots.txt group.\n\n- Where: [`/robots.txt`](https://poe2k.com/robots.txt)\n- How to find it: In robots.txt.\n- Specification: [Content Signals](https://contentsignals.org/), proposal\n\n### Shared training preference\n\n`User-agent: __usage_ai-training` with `Allow: /`: in favour of training, for every provider that reads it.\n\n- Where: [`/robots.txt`](https://poe2k.com/robots.txt)\n- How to find it: In robots.txt.\n- Specification: [draft-kelley-aipref-training-preference-signal](https://datatracker.ietf.org/doc/draft-kelley-aipref-training-preference-signal/), draft\n\n### TDMRep\n\n`tdm-reservation: 0`: no reservation against text and data mining.\n\n- Where: every response's header, [`/.well-known/tdmrep.json`](https://poe2k.com/.well-known/tdmrep.json)\n- How to find it: The header on every response; the file at its well-known address.\n- Specification: [TDM Reservation Protocol](https://www.w3.org/community/reports/tdmrep/CG-FINAL-tdmrep-20240510/), standard\n"
  }
}
