Agent readiness checker Can an AI agent reach, read and use your site?

Before an agent can do anything on your behalf it has to get in and understand what it is looking at. An agent readiness check scores that.

Check your site for free

Where this check stops, and why

Agent readiness has two halves. This scores the first one properly and does not touch the second.

Scored here

  • Whether named agents are blocked in robots.txt
  • Whether the page parses without running JavaScript
  • Whether a model can say what the business does
  • Whether it answers fast enough and over HTTPS

Not checked

  • agents.json
  • Anything under /.well-known/
  • An MCP server card
  • Declared actions an agent could call
It is a real subject
The right-hand column is a real and growing subject, and the guide covers what each file is for.
It is the second problem
A manifest sitting on a page an agent cannot read or understand buys nothing.
So the left column comes first
It is the one worth settling first, and the one almost every site fails on.

Three things before an agent can act

They happen in order, and the third is where nearly every site we check loses its points.

  1. Can AI find you?

    We read your robots file against twelve AI crawlers by name, then your sitemap and llms.txt.

  2. Can AI read you?

    We take the page before JavaScript runs: headings, structured data, and whether the words are there.

  3. Can AI trust you?

    HTTPS, a redirect that resolves, and a page that arrives before a crawler gives up.

What the check scores

Five categories, weighted. Every check behind the number is set out on the methodology page.

  • 58%

    Crawler access

    Your robots file, read against twelve crawlers

  • 82%

    Structure

    Schema, heading order, sitemap, llms.txt

  • 44%

    AI understanding

    What a model can name from the page alone

  • 90%

    Speed

    Mobile performance, and how fast the page answers

  • 68%

    Security

    HTTPS, and a redirect that resolves

What your report includes

All of it on screen the moment the scan finishes. No summary version, no upgrade.

example.com Falling behind
47 out of 100 Grade D

AI readiness score

  • Mostly invisible to AI
  • Falling behind

An AI engine gets about half of what it needs from this page.

  • Crawlability 50%
  • Structure 56%
  • AI understanding 16%
  • Speed 60%
  • Security 100%
  • 3 Critical
  • 1 High
  • 3 Medium
  • 1 Low

Also in it:

  • AI readiness score

    0 to 100, from 5 weighted signals, with a grade and a band.

  • Category scores

    Five of them: crawler access, structure, understanding, speed, security.

  • AI crawlers, by name

    12 agents across 6 engines, checked one at a time.

  • What a model could name

    Five facts: your business, services, products, industry and location.

  • Ranked fixes

    Every one, with what it is worth and how much work it is.

  • Scores per engine

    Four: ChatGPT, Claude, Gemini and Perplexity, weighted separately.

That is what comes back. Here is where to get it.

One page, read live, with your AI readiness score at the top and the full audit under it.

Run the free check

Where to start, depending on you

  • You have not checked before

    Start at the five category scores.

    They tell you in one look whether this is a writing problem or an engineering one. Usually it is writing.

  • You own the site

    Start at the ranked fixes.

    Each carries its points and its effort, so you know what you are buying before you ask.

  • You report to someone

    Send the report link.

    It has its own address and shows its arithmetic, so it survives a sceptical reader.

Questions about agent readiness

What is agent readiness?

Whether an AI agent, something acting on a person’s behalf rather than just answering them, can use your website. It has two halves: whether the agent can read the page at all, and whether you publish the files that tell it what actions are available. This checks the first half.

Does this check agents.json or an MCP server card?

No. We do not fetch agents.json, anything under /.well-known/ or an MCP card, and we would rather say so than let the page imply it. The guide to agent protocols covers what those files are and who is actually reading them, which today is fewer systems than the discussion suggests.

Is my site agent ready?

Run the check and you will have the foundation answered in under a minute: whether 12 named crawlers across 6 engines can reach you, whether your structure parses, and whether a model can say what you sell. A manifest on top of a page an agent cannot read is worth nothing, so this is the half to settle first.

How is agent readiness different from AI readiness?

In what happens after the reading. An answer engine reads your page and quotes it. An agent reads your page and then tries to do something: compare, book, buy, fill a form. The reading requirement is identical, which is why one scan covers both, and the acting requirement is where agents need more from you.

What stops an agent using a website?

Usually the same three things that stop any machine. The crawler is blocked in robots.txt. The content only exists after JavaScript runs. Or the page never states plainly what the business is, so the agent cannot tell whether it is even in the right place. Those are all in the report.

Do AI agents respect robots.txt?

The named crawlers from the large labs generally do, and that is what we test against. An agent operating on behalf of a signed-in person may identify differently or not at all, so robots.txt is the floor rather than the whole picture. Blocking a crawler reliably costs you the engine behind it.