{
 "acronym": "ARS",
 "adoption": {
  "by": null,
  "level": "unmeasured",
  "probe_run": null
 },
 "aliases": [
  "Vercel Agent Readability Spec"
 ],
 "analog": "a Lighthouse/PageSpeed-style audit checklist, but scored against agent readability rather than performance",
 "collisions": [
  "Agent-Friendly Documentation Spec (a separate, earlier spec by a different maintainer covering similar ground — see dispute)"
 ],
 "discovery": {
  "mechanism": "none — not a discoverable manifest; it is a checklist a site owner applies to their own pages, verified externally by tools like agent-ready.dev or is-agentic.com",
  "path": "none"
 },
 "dispute": {
  "claims": [
   "Vercel presents the checklist as authoritative guidance for 'AI-optimized websites'",
   "dacharycarey.com (maintainer of the Agent-Friendly Documentation Spec) argues platform-written specs like this one should be evaluated skeptically since Vercel both writes the spec and sells the hosting it recommends"
  ],
  "summary": "Vercel published this spec without an external standards process or a clear version/date, prompting at least one independent commentator to note it overlaps with, and was not coordinated with, a pre-existing 'Agent-Friendly Documentation Spec' maintained by someone else."
 },
 "evidence": [
  {
   "claim": "Full checklist text: site-level files (llms.txt, robots.txt, sitemap.xml/md, AGENTS.md), page-level HTML requirements (canonical link, meta tags, JSON-LD, heading structure, signal-to-noise ratio), server configuration (markdown mirrors, `Accept: text/markdown` content negotiation, `Link` header canonical), content quality (fenced code blocks, OpenAPI schema links), and the scoring formula",
   "date": "2026-03",
   "label": "VERIFIED",
   "url": "https://vercel.com/kb/guide/agent-readability-spec"
  },
  {
   "claim": "Independent commentary identifies the author as Timothy Jordan, notes the page carries no publication date and was 'last updated March 23' (2026), and frames it as a competing effort alongside a pre-existing 'Agent-Friendly Documentation Spec' maintained separately",
   "date": "2026-03-28",
   "label": "REPORTED",
   "url": "https://dacharycarey.com/2026/03/28/how-to-evaluate-platform-written-spec/"
  },
  {
   "claim": "A third-party checker, agent-ready.dev, scores sites specifically 'against the Vercel Agent Readability Spec and llmstxt.org standard', indicating at least one independent implementation of the scoring logic",
   "date": "2026",
   "label": "REPORTED",
   "url": "https://agent-ready.dev/"
  }
 ],
 "form": "document-format",
 "governance": "Vercel; published in Vercel's own Knowledge Base with no external standards process",
 "group": null,
 "history": [
  {
   "date": "2026-09-06",
   "note": "new record added during read-step verification; verified against vercel.com/kb/guide/agent-readability-spec and independent commentary"
  }
 ],
 "id": "vercel-agent-readability",
 "implementation": "shipping",
 "last_verified": "2026-09-06",
 "name": "Agent Readability Spec",
 "native_status": "A specification and scoring checklist, not a protocol; framed as best practices to implement voluntarily",
 "origin": {
  "date": "2026-03",
  "org": "Vercel (Timothy Jordan)"
 },
 "part_of": null,
 "parties": [
  "agent-site"
 ],
 "phase": "draft",
 "probe": {
  "method": "GET",
  "on_absent": "A site failing most checks is not in violation of anything; the spec is a voluntary readiness checklist, not an enforced requirement",
  "parse": "No single field proves conformance; the spec defines ~20 discrete site- and page-level checks (llms.txt served, robots.txt allows AI bots, AGENTS.md present, canonical link, JSON-LD, markdown mirrors, Accept: text/markdown negotiation, etc.) each independently verifiable by curl, and a numeric score = round(passed/total * 100)",
  "path": "{origin}/ (plus /llms.txt, /robots.txt, /sitemap.xml, /sitemap.md, /AGENTS.md as sub-checks; see the spec's own per-requirement curl commands)"
 },
 "question": "How readable is this site's content for AI agents, and what specifically should be fixed?",
 "scope": "general",
 "spec_url": "https://vercel.com/kb/guide/agent-readability-spec",
 "step": "read",
 "summary_md": "Vercel's Agent Readability Spec is a checklist and 0-100 scoring system for how well a website's content can be discovered, fetched, and understood by AI agents [1]. It groups roughly twenty independently verifiable checks into three areas: discovery (an `llms.txt` file, a permissive `robots.txt`, XML and markdown sitemaps), structure (canonical links, meta tags, Schema.org/JSON-LD, heading hierarchy, text-to-HTML ratio), and context (an `AGENTS.md` skill file, markdown mirrors of HTML pages, `Accept: text/markdown` content negotiation, fenced and language-tagged code blocks, OpenAPI/Swagger schema links) [1].\n\nIt solves the problem of turning \"be agent-friendly\" into a concrete, curl-verifiable punch list: each requirement in the spec ships with an example and a shell command to check it, and site owners get a single percentage score (`passed / total × 100`) they can track over time [1]. Notably, it documents — by name, as Vercel's own recommended practice — serving a markdown alternate for every HTML page and returning it when a client sends `Accept: text/markdown`, with a `Link` header pointing back to the canonical HTML URL [1]. This is the same content-negotiation pattern also described in llms.txt v2's discovery mechanism (see the `llms-txt` record) and is the clearest documented instance of the general \"markdown twin\" practice found during this verification pass.\n\nIt does not solve trust or accuracy: nothing in the spec checks whether the content is correct, and a perfect score says only that a page is structurally easy to fetch and parse, not that an agent's answer using it will be right. It is also not a protocol or a machine-readable manifest — there is no fixed path an agent fetches to learn a site's score; the checklist is meant to be run by (or on behalf of) the site owner, and scoring is reproduced by third-party tools rather than looked up from a canonical registry.\n\nCurrent state, as of this verification (September 2026): the page itself carries no publication date or version number. An independent commentator dated it to \"last updated March 23\" (2026) and noted its author is Timothy Jordan [2]. At least one third-party checker, agent-ready.dev, implements scoring explicitly described as checking a site \"against the Vercel Agent Readability Spec and llmstxt.org standard,\" which is the clearest evidence of independent implementation found [3]; Vercel's own knowledge-base article is the only primary specification text.\n\nWhat is disputed or unknown: the spec was published unilaterally by a hosting vendor, with no external review process, and overlaps substantially with an earlier, separately maintained 'Agent-Friendly Documentation Spec' — a secondary source flagged this as worth scrutinizing given Vercel's commercial interest in the hosting practices the spec implicitly favors (server-rendered pages, content negotiation infrastructure) [2]. No independent adoption count or measurement of how many sites meet a given score threshold was found.",
 "track": "single-vendor",
 "version": {
  "date": "2026-03",
  "label": "current (last updated 2026-03-23 per a secondary source; no version number or publication date is given on the page itself)"
 },
 "url": "https://agenticweb.wiki/protocols/vercel-agent-readability/",
 "category": "read",
 "type": "protocol"
}