---
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."
url: "https://poe2k.com/agents"
---

# Agents

> 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.

`<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.

## Read the pages

Every page reads without JavaScript, and has the same content as Markdown and its facts as JSON-LD.

### Markdown of every page

A 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.

- Where: `<page>.md` ([`/db/tools.md`](https://poe2k.com/db/tools.md))
- How to find it: `<link rel="alternate" type="text/markdown">` in the head.
- Specification: [Per-page Markdown source endpoints](https://specification.website/spec/agent-readiness/markdown-source-endpoints/), convention

### llms.txt

What poe2k is, how to describe it, and an index of the sections; each section has its own scoped llms.txt.

- Where: [`/llms.txt`](https://poe2k.com/llms.txt), `<section>/llms.txt` ([`/db/llms.txt`](https://poe2k.com/db/llms.txt))
- 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.
- Specification: [The /llms.txt file (v2)](https://llmstxt.org/), convention

### Structured data

Typed 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).

- Where: each page's head, as an application/ld+json script
- How to find it: In the HTML before any script runs.
- Specification: [schema.org in JSON-LD](https://schema.org/), standard

### Schemamap

Each page's JSON-LD graph on its own, and an index of them with their schema.org types.

- Where: `<page>.jsonld` ([`/db/tools.jsonld`](https://poe2k.com/db/tools.jsonld)), [`/schemamap.xml`](https://poe2k.com/schemamap.xml)
- 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.
- Specification: [Schemamap](https://specification.website/spec/agent-readiness/schemamap/), proposal

## Find what exists

Each of these answers "what does this site offer" from one fetch, without reading any page.

### Link headers

Every 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.

- Where: every response
- How to find it: `curl -sI https://poe2k.com/`
- Specification: [RFC 8288: Web Linking](https://www.rfc-editor.org/rfc/rfc8288), standard

### API catalog

A linkset of every API and machine-readable resource, each with its description and documentation.

- Where: [`/.well-known/api-catalog`](https://poe2k.com/.well-known/api-catalog)
- How to find it: `Link: <…>; rel="api-catalog"` on every response.
- Specification: [RFC 9727: api-catalog](https://www.rfc-editor.org/rfc/rfc9727), standard

### AI catalog

The Agent Skill, with its media type and example questions.

- Where: [`/.well-known/ai-catalog.json`](https://poe2k.com/.well-known/ai-catalog.json)
- How to find it: `Agentmap:` in robots.txt, `rel="ai-catalog"` in the head and the `Link` header.
- Specification: [Agentic Resource Discovery](https://specification.website/spec/agent-readiness/agentic-resource-discovery/), draft

### Agent Skill

A SKILL.md that teaches an agent when to use poe2k and how to read it; the index has its sha256 digest.

- 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)
- How to find it: `Link: <…>; rel="agent-skills"` and the API catalog.
- Specification: [Agent Skills Discovery (v0.2.0)](https://github.com/cloudflare/agent-skills-discovery-rfc), draft

### Page index

Every page as JSON with its addresses, section, schema.org types, headings, update and token estimate.

- Where: [`/agents/pages.json`](https://poe2k.com/agents/pages.json)
- How to find it: The API catalog and the Agent Skill.
- Specification: [poe2k's own: AgentPage, in the file itself](https://poe2k.com/agents/pages.json), convention

### Sitemap

Every page search engines get, with its last change where the page knows it.

- Where: [`/sitemap.xml`](https://poe2k.com/sitemap.xml)
- How to find it: `Sitemap:` in robots.txt and the `Link` header.
- Specification: [Sitemaps XML format](https://www.sitemaps.org/protocol.html), standard

### AI Discovery Document

The news API's actions, for agents that read this draft.

- Where: [`/.well-known/ai`](https://poe2k.com/.well-known/ai)
- How to find it: The API catalog.
- Specification: [draft-aiendpoint-ai-discovery-01](https://datatracker.ietf.org/doc/html/draft-aiendpoint-ai-discovery-01), draft

## Feeds and APIs

News in the formats feed readers and agents already read.

### RSS and JSON Feed

Every overlay release and every post, newest first, in full.

- Where: [`/feed.xml`](https://poe2k.com/feed.xml), [`/feed.json`](https://poe2k.com/feed.json)
- How to find it: `<link rel="alternate">` in the head and the `Link` header.
- Specification: [RSS 2.0 and JSON Feed 1.1](https://www.jsonfeed.org/version/1.1/), standard

### News API

Every published article as JSON, and each one with its Markdown; read-only, no auth.

- Where: [`/api/news/all.json`](https://poe2k.com/api/news/all.json), [`/api/news/openapi.json`](https://poe2k.com/api/news/openapi.json)
- How to find it: The API catalog names the OpenAPI document as the API's `service-desc`.
- Specification: [OpenAPI 3.1](https://spec.openapis.org/oas/v3.1.0), standard

## What agents may do with it

poe2k wants to be read, cited and learned from: every crawler may fetch everything, for search, live answers and training.

### robots.txt, by name

Allows everyone, and names the AI crawlers (GPTBot, ClaudeBot, PerplexityBot and others), so the policy is explicit.

- Where: [`/robots.txt`](https://poe2k.com/robots.txt)
- How to find it: At its fixed address.
- Specification: [RFC 9309: Robots Exclusion Protocol](https://www.rfc-editor.org/rfc/rfc9309), standard

### Content Signals

`Content-Signal: search=yes, ai-input=yes, ai-train=yes` in each robots.txt group.

- Where: [`/robots.txt`](https://poe2k.com/robots.txt)
- How to find it: In robots.txt.
- Specification: [Content Signals](https://contentsignals.org/), proposal

### Shared training preference

`User-agent: __usage_ai-training` with `Allow: /`: in favour of training, for every provider that reads it.

- Where: [`/robots.txt`](https://poe2k.com/robots.txt)
- How to find it: In robots.txt.
- Specification: [draft-kelley-aipref-training-preference-signal](https://datatracker.ietf.org/doc/draft-kelley-aipref-training-preference-signal/), draft

### TDMRep

`tdm-reservation: 0`: no reservation against text and data mining.

- Where: every response's header, [`/.well-known/tdmrep.json`](https://poe2k.com/.well-known/tdmrep.json)
- How to find it: The header on every response; the file at its well-known address.
- Specification: [TDM Reservation Protocol](https://www.w3.org/community/reports/tdmrep/CG-FINAL-tdmrep-20240510/), standard
