AINativeainative.axAX AUDIT
← AX Audit
AX AUDIT VS. AGENTREADY.ORG

AX Audit vs. the AgentReady.org standard

AgentReady.org publishes an open, vendor-neutral specification for agent readiness — not a scanner of its own. Here's how its spec sections map to AX Audit's categories, and the one surface its spec doesn't define yet.

AgentReady.org is a specification, not a scoring product — it defines requirements under three phases (Find, Read, Act) with stable IDs like AR-FIND-01 and AR-ACT-03. AX Audit uses its own category taxonomy (AR-DISC, AR-CONT, AR-CAP, AR-AUTH, AR-COMM) covering the same general ground — discoverability, machine-readable content, callable capabilities, delegated identity, and agentic commerce — in the same spirit as the open standard, though the exact category boundaries and IDs differ between the two. Neither AgentReady.org's Find/Read/Act phases nor its listed requirements (AR-ACT-01 through AR-ACT-10, as published) define anything about an agent provisioning or creating an account — that's what AX Audit's AR-PROV category adds.

What the AgentReady.org spec defines

Source: agentready.org and github.com/agentready-org/standard (spec v1.0, August 2026).

Find
robots.txt / bot access, first-party docs, sitemap.xml, AI catalog
Read
server-rendered HTML, proper HTTP status codes, llms.txt, JSON-LD, Markdown mirrors
Act
agent-compatible auth, OpenAPI, MCP server, SDK/CLI, agent payment processing

Category-by-category

CATEGORY
AX AUDIT
AGENTREADY.ORG
Discoverability (robots.txt, sitemaps, docs, AI catalog)
Scored — AR-DISC
Defined — "Find" phase (AR-FIND-01..04)
Machine-readable content (HTML, llms.txt, JSON-LD)
Scored — AR-CONT
Defined — "Read" phase (AR-READ-01..11)
Capability surfaces (MCP, OpenAPI, SDK/CLI)
Scored — AR-CAP
Defined — part of "Act" phase (AR-ACT-02/03/04/06)
Identity & delegated access
Scored — AR-AUTH
Defined — "Act" phase, agent-compatible auth (AR-ACT-01)
Agentic commerce / payments
Scored — AR-COMM
Defined — "Act" phase, agent payment processing (AR-ACT-08)
Can an agent open an account with you?
Scored — AR-PROV (AINative-defined category)
Not defined in the published spec (as of v1.0, Aug 2026)
AR-PROV · THE HONEST DIFFERENCE

Can an agent actually open an account with you?

Every tool on this page — including this one — checks whether agents can find and read your site, and most now check whether they can transact with it. None of the three we compare against here define or score agent-initiated account provisioning: machine-readable terms, credential issuance, and signed-mandate consent, so an agent can sign up and get configured without a human filling out a form. AX Audit calls that AR-PROV. It's AINative's own extension to the taxonomy, not a repackaging of someone else's check.

What AX Audit checks

10+ signals across 6 AR-* categories (AR-DISC, AR-CONT, AR-CAP, AR-AUTH, AR-COMM) plus AR-PROV — the only one of the three that checks agent-provisioning readiness.

AR-DISC
Discoverability
robots.txt · A2A Agent Card · llms.txt · sitemaps
AR-CONT
Content
JSON-LD · Markdown negotiation · canonical metadata
AR-CAP
Capabilities
MCP server card · OpenAPI 3.1 · API Catalog (RFC 9727)
AR-AUTH
Identity & Access
OAuth 2.0 + PKCE · RFC 8414/9728 · OIDC · Web Bot Auth
AR-COMM
Commerce
x402 · ACP · UCP · MPP
AR-PROV · ours
Provisioning
account-create · machine-readable terms · credential issuance · signed-mandate consent
HOW WE CHECKED THIS

Verified directly from agentready.org and its public spec repository: the Find/Read/Act phase structure and the AR-FIND/AR-READ/AR-ACT requirement IDs listed above. Note AgentReady.org's "AR-*" IDs and AINative's "AR-*" category names are not the same taxonomy — they share a prefix by convention, not by shared authorship, and the category boundaries don't map one-to-one. We did not find any requirement in the published spec covering agent-initiated account provisioning or KYC. AgentReady.org itself does not run a scanner — scoring is left to independent tools, which is why this page compares AX Audit against the standard's defined scope rather than against any specific scoring product.

See where your site actually stands

Free scan, about 60 seconds. Six categories plus AR-PROV — the one none of these tools check yet.

Run a free AX Audit →