--- url: https://ora.ai/blog/agentready-launch title: "Introducing AgentReady.org: the first open standard for AX" description: "AgentReady is an open standard for what a product should implement so agents can use it, built from measured agent behavior. We maintain it with Vercel, Stripe, Auth0, Mintlify, Tavily, Google, Elementor, and MIT." crawled_at: 2026-10-29T01:02:47Z lastmod: 2026-10-19 ask: https://ora-ai.ora.run/ask docs: https://ora-ai.ora.run/.well-known/ora/docs lang: en --- # Introducing AgentReady.org: the first open standard for AX ora · Oct 19, 2026 · 5 min read [Share on X](https://x.com/intent/tweet?text=Introducing%20AgentReady.org%3A%20the%20first%20open%20standard%20for%20AX&url=https%3A%2F%2Fora.ai%2Fblog%2Fagentready-launch) [Share on LinkedIn](https://www.linkedin.com/sharing/share-offsite/?url=https%3A%2F%2Fora.ai%2Fblog%2Fagentready-launch) Agents are a new class of user, and there is still no shared definition of what it takes to be ready for them. Today we are launching AgentReady.org , an open standard for what a product should implement so agents can use it, together with partners who build and study the surfaces agents touch every day: Vercel, Stripe, Auth0, Mintlify, Tavily, Google, Elementor, and MIT. MCP, WebMCP, A2A, x402, llms.txt, Web Bot Auth. The agentic web has more protocols every quarter, and most readiness checklists simply list them. A list says what exists. It cannot say what matters, because nobody measured it. So our research lab ran agents on real tasks more than 250,000 times, and ran a controlled experiment that changed one thing at a time. AgentReady is built from that evidence. Here is what it showed. finding 01 ## Two changes broke an agent To separate what helps from what decides, we served one docs site under 19 configurations and asked two clients to pull a planted answer from it: a plain fetch, like most agent tools, and a client that runs JavaScript. Almost nothing changed the outcome. Hiding the answer behind JavaScript did, and so did blocking agents. Controlled experiment answer retrieved, per topic | Site configuration | Plain fetch | Runs JS | |---|---|---| | Answer only in JavaScript 1 configuration | 0/5 failed | 5/5 retrieved | | 403 to agent user agents 2 configurations | 0/5 failed | 0/5 failed | | Every other configuration 16 configurations, including llms.txt, JSON-LD, sitemaps, and markdown mirrors | 5/5 retrieved | 5/5 retrieved | One docs site served under 19 configurations, probed on 5 topics by a plain fetch client and a client that runs JavaScript (190 probes). Only two kinds of change stopped a client from retrieving the answer. finding 02 ## Agents read the same pages people do Agents went where human visitors go: the homepage first, then the docs. Files built only for machines were reached far less often. Agents asked for markdown on about 65% of fetches, but markdown mirrors and content negotiation never changed whether they succeeded. Where agents go % of traced runs docs pages · 83 % · homepage · 69 % · then a cliff · .well-known/* · 23 % · openapi.json on sites that ship one 21 % · sitemap.xml · 4 % Share of traced runs that reached each surface at least once. finding 03 ## Links beat guessed paths When agents did open a file like llms.txt, they almost always got there by following a link from a page they had already read, not by guessing the path. How agents reached each file % of fetches via a link openapi.json · 97 % · .well-known/* · 93 % · llms.txt · 86 % Share of fetches that arrived through a link rather than a guessed path. finding 04 ## When agents cannot read you, they answer without you An agent that cannot read a site still answers, from search results and other people’s pages. Across 1,056 business sites, those answers were 3.7× as likely to miss every fact the user asked for, and agents clearly recommended agent-ready businesses almost twice as often. Answers about a business 1,056 sites Clearly recommends the business · agent-ready · 20 % · not agent-ready · 11 % Contains none of the facts asked for read from the site · 7 % · from the web · 25 % Recommendation: two blind judges both gave the top grade. Missing facts: 2,499 graded answers across 131 businesses. From AX is the New AEO . ## From findings to essentials Each finding sets a strength. MUST marks what an agent fails without: the two changes that broke an agent in our experiment, and, when agents should finish a task, an MCP server or a CLI to act through. SHOULD covers practices that changed where agents went, and the surfaces that make acting reliable, like a public API and WebMCP on the pages agents act through. MAY covers conventions that are emerging but not yet proven, like agent payments, where early numbers are strong: agents paying through Link got 92.3% of test checkouts right. The spec lists them in the order agents meet a site: find, read, act. The essentials find, read, act find every site - MUST Allow agents in robots.txt and bot protection - SHOULD Publish the answer as first-party docs - SHOULD List pages in a sitemap.xml - MAY Publish an AI Catalog read every site - MUST Put the answer in the initial HTML - MUST Return real HTTP status codes - SHOULD Link llms.txt, JSON-LD, and OpenAPI - SHOULD Fence and language-tag code act when agents should finish a task - MUST An MCP server or a CLI, at least one - SHOULD Auth an agent can finish - SHOULD A public API with OpenAPI - SHOULD WebMCP on pages agents act through - MAY Agent payments and NLWeb MUST: an agent fails without it. SHOULD: changed where agents went, or makes acting reliable. MAY: emerging, not yet proven. ## What it is not AgentReady names what to implement. It does not score anyone. There are no weights, thresholds, or badges in the spec, and that is why companies that compete elsewhere can maintain it together. It is vendor neutral, MIT licensed, and developed in the open. Scoring is left to implementations, and three public rankers already read the same spec for different jobs. is-agentic.com (which we built with Vercel) scores the essentials for sites whose job is content. Our own ranker, ora.ai , scans every requirement in the spec end to end, from discovery and docs through auth, MCP, and payments. mintlify.com/score grades documentation. Their checks and weights can change without changing the spec. ## How the standard evolves The agentic web changes every month, so the spec has to change with it. New conventions usually enter as MAY. They move to SHOULD or MUST only when our studies show they change what agents do, and they move back down when they stop mattering. Every requirement has a stable identifier, such as AR-FIND-01 , every number in the spec names its source, and every change is recorded in a public changelog. Each committee member reviews the part of the agent journey they know best: - Ora (us), research. We run the studies behind every requirement and keep the data public. - Vercel, infrastructure and web essentials. Whether agents can reach a page and read the answer in it. - Mintlify, docs. How to build docs that agents read and cite. - Auth0, auth. How agents sign in and act on a user’s behalf. - Stripe, payments. What to build so agents can pay you. - Tavily, search. Whether agents find you when they search the web for a task. - Elementor, WordPress and site building. How sites can be agent-ready by default. ## Get involved Read the spec at agentready.org , or give it to your agent through agentready.org/llms.txt . For a hands-on version, Vercel’s guide [Make your site readable by AI agents](https://vercel.com/kb/guide/make-your-site-readable-by-ai-agents) walks through each essential with code. The source and the discussion live on [GitHub](https://github.com/agentready-org/standard) . If you maintain a protocol, run agent infrastructure, or have agent runs that contradict a requirement, open an issue. The spec changes when the evidence does. ### Want to see where you rank? Run the same scan we ran on thousands of sites. Free, public, takes about 1 minute. Scan your site → Explore the data ← all posts # Footer The standard for agent experience. © 2026 [era labs](https://eralabs.ai/) Product - Scan a site - [Journey](https://journey.ora.ai/) - [WebMCP audit](https://webmcp.ora.ai/) - [Directory](https://directory.ora.ai/) Resources - Methodology - Research - Blog - API Docs Company - About - Contact - Privacy - [@oradotai](https://x.com/oradotai)