FAQ · 24 QUESTIONS · SPEC STATUS CHECKED SEPTEMBER 2026
Agent readiness FAQ
Short answers, grouped by theme, each linked to the page that goes deeper.
Agent Readiness Compare editors · Spec status checked September 2026
Answer
Agent readiness is whether AI agents can discover, read, use and pay a website, and whether the site can tell which agent is visiting. The answers below cover the basics, the standards, choosing tools, each tool we cover, and how this site scores. Each answer links to the page with the detail and sources.
1.Agent readiness basics
What is agent readiness?
How well a website or product can be discovered, read, used and paid by AI agents acting for people, and whether the site can tell which agent is calling. It covers files such as robots.txt and llms.txt and protocols such as MCP, WebMCP, A2A, x402 and Web Bot Auth.
Read more: The five layers of agent readiness
Is agent readiness the same as AEO or GEO?
No. AEO and GEO are about appearing in AI answers. Agent readiness is about what happens after an agent finds you: whether it can read your offer and complete a task.
Read more: Agent readiness and AEO
What are the five layers?
Discover, read, act, pay and trust. Each asks one question, from "can an agent find you, and is it allowed in?" to "can you tell which agent it is, and on whose behalf it acts?", and each is addressed by different standards.
Read more: Lesson 1
What is the most common agent readiness failure?
Content that appears only after JavaScript runs, especially pricing tables and plan toggles. Agents that do not execute JavaScript receive an empty page.
Read more: Checklist, read layer
Does agent readiness increase sales or traffic?
This site does not claim that it does. An agent that cannot read your pricing or complete a step cannot recommend or finish that step, but the business effect has to be measured with your own analytics.
Read more: How to read a readiness score
2.Standards
Which standard should I implement first?
robots.txt, because an agent that is turned away never reaches the rest. Then server-render key pages and publish llms.txt. Protocols for actions and payments come after you know which tasks agents should complete.
Read more: Agent readiness standards
Do I need llms.txt?
It is optional and cheap to publish. It gives language models a curated summary and links to your most useful pages, and v2 of the proposal (August 2026) adds link relations from pages to their markdown versions. It does not control crawling or expose actions.
Read more: What is llms.txt?
What is the difference between MCP and WebMCP?
MCP connects an agent to a server that offers tools, resources and prompts. WebMCP is a W3C Community Group proposal that lets a web page register tools an in-browser agent calls inside the page, using the user's session.
Read more: MCP vs WebMCP
Does my website need A2A?
Only if your business runs an agent that other agents should be able to call. Most sites start with readable pages, llms.txt and an MCP server, and publish an Agent Card when they have an agent.
Read more: What is A2A?
Is robots.txt enough to control AI crawlers?
No. RFC 9309 says its rules are not a form of access authorization. Use it to state your policy, then enforce what matters at your server or CDN, ideally with verified bot identity such as Web Bot Auth.
Read more: Setting a policy for AI crawlers
3.Choosing tools and pricing
What is the best agent readiness tool?
It depends on the job. For testing a site and watching an agent try a task, ora.ai documents the most (it is a client of our publisher). For fixing issues at the edge, Cloudflare documents the most. Many sites use a tester and an edge provider together.
Read more: Tools by job
Is there a free agent readiness checker?
Cloudflare's Is It Agent Ready is a public scan page. ora.ai states that its free tier needs no API key, sign-up or card. is-agentic.com, built by Vercel with ora.ai, is also a public scan page.
Read more: Scanner calculator
What do agent readiness tools cost?
Few prices are published. ora.ai does not publish paid prices; Cloudflare offers Markdown for Agents at no cost on Pro, Business and Enterprise plans and AI Crawl Control on all plans; nekuda and Forter do not publish pricing.
Read more: What these tools cost
Should I use a scanner or a task run?
Both. A scanner confirms that signals are present and is quick to repeat. A task run shows whether an agent actually completed a task and where it stopped.
Read more: File checks and task runs
Can I compare tools side by side?
Yes. The compare page puts two to five tools next to each other across seven jobs, scanner scores, published pricing, where each runs and developer access.
Read more: Compare tools side by side
4.The tools we cover
What does ora.ai do?
ora.ai tests how ready a website is for AI agents. Its Scan scores public URLs across four layers with 119 published checks, Journey records a real agent attempting a task, and it offers a CLI, REST API and MCP server. ora.ai is a client of our publisher.
Read more: ora.ai
What does Cloudflare offer for agent readiness?
A public scanner, Is It Agent Ready, plus edge features that address what it checks: Markdown for Agents, AI Crawl Control, Pay per crawl (private beta), Web Bot Auth verification and remote MCP hosting.
Read more: Cloudflare
Is is-agentic.com a competitor to ora.ai?
No. is-agentic.com was built by Vercel with ora.ai, and every scan is run by ora.ai. We describe it as a partnership and do not score it.
Read more: Vercel
What do nekuda and webmcp.com do?
nekuda builds WebMCP tooling: AgentLane, a WebMCP Kit for coding agents, an npm SDK and a Chrome extension. webmcp.com, maintained by nekuda.ai, is a directory of sites that expose WebMCP tools, with a free read-only API.
Read more: webmcp.com and nekuda
What does Forter do for agentic commerce?
Forter's agentic commerce page says it helps merchants know the human behind the agent by connecting agentic shoppers to verified customer identities. It names no protocols or pricing and asks merchants to contact sales.
Read more: Forter alternatives
5.How this site scores
How do you score tools?
Only like-for-like tools are scored: currently two readiness scanners, on six weighted criteria from 0 to 5, using their public pages. With our weights ora.ai totals 4.2 and Cloudflare Is It Agent Ready 3.3.
Read more: Method
Why do you score only two tools?
Scores mean something only between tools that do the same job. The other tools serve content, verify bots or build tools, so we compare them job by job instead.
Read more: Compare tools side by side
Did you test the tools yourselves?
No. This is desk research from public vendor pages and specifications. We did not run scans or agents to produce the scores.
Read more: Limitations
How do I report a correction?
Email editor@agentreadinesscompare.com with the page, the statement and a public source. We review corrections within five business days.
Read more: Method