Agent Readiness Checker: is your site AI-agent ready?

[Chat Thing](https://chatthing.ai/)

Open main menu

- Features
- Use Cases
- [Pricing](https://chatthing.ai/#pricing)
- Resources

[Log in](https://app.chatthing.ai/app/auth/login) [ Book a demo](https://chatthing.ai/demo) [Sign up](https://app.chatthing.ai/app/auth/register)

[← Back to blog](https://chatthing.ai/blog)Blog # How ready is your website for AI agents? Now there's a free way to check

![Zef](https://res.cloudinary.com/djyjvrw5u/image/upload/v1710941716/IMG_2278_d3b5e4fa69.jpg)

Zef

14 Jul 2026

~ 6 min read

---

![How ready is your website for AI agents? Now there's a free way to check](https://res.cloudinary.com/djyjvrw5u/image/upload/v1783957835/hero_91cf981c76.png)

---

### On this page

1. [No single vanity score](#no-single-vanity-score)
2. [The check most sites fail](#the-check-most-sites-fail)
3. [It knows a marketing site from a SaaS](#it-knows-a-marketing-site-from-a-saa-s)
4. [The part that makes it different: you can argue with it](#the-part-that-makes-it-different-you-can-argue-with-it)
5. [We call out the hype, too](#we-call-out-the-hype-too)
6. [A few moves the audit can't score, but you should still make](#a-few-moves-the-audit-cant-score-but-you-should-still-make)
7. [Go and check your site](#go-and-check-your-site)

Here's the uncomfortable bit up front: a growing share of the visitors deciding whether to recommend your product are not people. They're AI agents. ChatGPT, Perplexity, Claude and the new wave of agentic browsers are reading the web on someone's behalf, summarising it, comparing it, and increasingly acting on it. And most websites were built for human eyes, not for a machine that never renders your JavaScript.

We know this because we can watch it happen. Chat Thing runs behind Cloudflare, and on a normal day our own properties field around 4,000 requests from AI crawlers - GPTBot, ClaudeBot, Amazonbot, PerplexityBot, CCBot and a dozen others - and that number climbs every fortnight. The agentic web isn't a forecast. It's already knocking, and for most sites nobody's checked whether it can get in.

So we built a free tool to tell you exactly where you stand. It's called the [Agent Readiness Checker](https://chatthing.ai/tools/agent-readiness-checker), and you can run it on any URL right now.

Think of it as a Lighthouse for the agentic web. You give it a site, it does a real scan, and it tells you how well AI agents and LLMs can discover, understand and actually use it.

## No single vanity score

The first decision we made was to not give you one big number.

ChatGPT, Perplexity, Claude and Google's AI behave very differently. One crawls, another cites, another executes. Collapsing all of that into a single "87/100" would be tidy but misleading, so we don't. Instead you get scored across four categories - can agents **discover** your content, can they **read** it, can they **act** on it, and can they **trust** it - and you get a read per engine, because a site that's perfect for Perplexity can still be a wall to ClaudeBot.

![The Agent Readiness Checker report: four categories scored independently, a plain-English AI summary, and Sprocket talking through the results on the left.](https://res.cloudinary.com/djyjvrw5u/image/upload/v1783958031/report_4c061a8d39.png)_The report scores each category on its own. There is deliberately no single overall number._

## The check most sites fail

The headline finding, over and over, is the same one.

Most of the big AI crawlers - GPTBot, ClaudeBot, PerplexityBot - do not run JavaScript. Only Google really renders. So if your content only appears after the page hydrates in the browser, a huge slice of the agentic web sees an empty shell where your product should be. The checker launches a real headless render, diffs the raw HTML against the rendered DOM, and shows you the gap. It's the single highest-weighted check we run, because it's the one that quietly costs you the most.

From there it works down through the things that actually matter: whether your robots.txt is accidentally blocking the citation crawlers you're trying to attract, whether your structured data agrees with what's on the page, whether an agent could complete a transaction on your site at all. That last one is the part almost nobody audits. Most tools stop at "can a crawler reach you". We also look at whether an agent could take an action - use an API, follow a commerce protocol, actually do the thing - because that's where the agentic web is heading.

## It knows a marketing site from a SaaS

Here's something a generic checklist gets badly wrong: it grades every site against the same list. But the right list for a brochure site is not the right list for a SaaS with an MCP server, and it's different again for a docs site or a shop.

So before it scores anything, the checker works out what kind of site you are - marketing, docs, SaaS or ecommerce - and re-weights the whole audit around that. A missing commerce protocol is a real gap for a shop and completely irrelevant for a marketing page, so on the marketing page it's marked N/A rather than counted against you. An llms.txt matters far more for docs that coding agents crawl than for a landing page. And if it guesses your type wrong, you just tell it, and it re-scores on the spot.

![The report showing a detected site type of "SaaS", with the reasoning and one-click options to reclassify as Marketing, Docs, SaaS or Ecommerce.](https://res.cloudinary.com/djyjvrw5u/image/upload/v1783958032/site_type_e64177305d.png)_The audit is tailored to your kind of site, so you're never marked down for missing something you'd never need._

## The part that makes it different: you can argue with it

A static report tells you what's wrong. It doesn't help you fix it.

So the Agent Readiness Checker isn't a report you read, it's an agent you talk to. Once the scan finishes, you can just ask it things. "Why is my machine-readability score low?" "Which of these actually matters for a SaaS site?" "Show me what a fixed robots.txt would look like." It answers grounded in your real results - it won't invent numbers - and it can generate concrete fixes on the spot: a corrected robots.txt, a starter llms.txt, a remediation brief you can paste straight into Cursor or Claude Code.

![Sprocket generating a starter llms.txt on the canvas, with a frank note that llms.txt is low-value for most sites, and a prompt to build your own agent.](https://res.cloudinary.com/djyjvrw5u/image/upload/v1783958034/suggested_fix_1597e67568.png)_Ask a question, get a grounded answer and a concrete fix - generated live on the report canvas._

It's the difference between being handed a diagnosis and being handed a diagnosis plus someone who'll sit with you and work through it.

And here's the sales bit, because I'd rather just say it plainly: that assistant is a Chat Thing agent. The whole experience - the chat, the live scan, the report updating in front of you - is one agent we built on our own platform. The tool doesn't describe what Chat Thing does. It is Chat Thing, doing it. If you've ever wondered what a properly capable agent trained on your own data and wired up to real tools feels like, run the checker and then have a conversation with it.

## We call out the hype, too

You can't build a trustworthy audit tool and then repeat every bit of AI-readiness folklore going.

So the agent will tell you, unprompted, that llms.txt is widely talked up but weakly evidenced - most of those files get essentially zero agent traffic. It'll tell you that schema is hygiene, not a magic citation lever. It flags the genuinely emerging standards as opportunities, not as failures you should panic about. The goal was an audit that's actually useful, not a checklist designed to make you feel behind so we can sell you the cure.

## A few moves the audit can't score, but you should still make

Some of the best things you can do for agent readiness aren't pass-or-fail checks, so the tool won't grade them. It'll happily talk you through them, though, and they're worth doing anyway.

The theme is simple: make your content trivially easy to lift. Add a "Copy as markdown" button to your docs and blog posts, so a human (or the agent they're driving) can grab clean, structured text in one click instead of wrestling with your HTML. Put an "Open in ChatGPT" or "Ask Claude about this page" action on key pages, so someone reading can hand the whole thing to an agent without copy-pasting. Serve a clean markdown version of each page for the crawlers that ask for it.

We practise this ourselves: every report the checker produces has a "Copy for your AI agent" button that hands over a tidy remediation brief you can paste straight into a coding agent. The easier you make it for an agent to take your content and run with it, the more often it will.

## Go and check your site

It's free, it takes about a minute for the first scan, and you'll come away knowing exactly where your site stands with the agents that are increasingly deciding whether your product gets recommended.

[Run the Agent Readiness Checker](https://chatthing.ai/tools/agent-readiness-checker) on your site. Then ask the agent what to fix first.

And if you like what that agent can do, you can build one for your own site with [Chat Thing](https://chatthing.ai) - point it at your docs, give it a few power-ups, and let it answer, act and convert for you.

### Related articles

[![Connect Your AI Agent to 8,000+ Apps with Zapier](https://res.cloudinary.com/djyjvrw5u/image/upload/v1782482565/zapier_hero_debe7969e3.jpg)](https://chatthing.ai/blog/zapier) [<h4>Connect Your AI Agent to 8,000+ Apps with Zapier</h4>](https://chatthing.ai/blog/zapier)

Connect your Chat Thing agent to 8,000+ apps with Zapier. Book meetings, update CRMs, post to Slack, all in one conversation.

[![The work you don't see (and why it makes Chat Thing better)](https://res.cloudinary.com/djyjvrw5u/image/upload/v1780301027/og_A_engine_room_b535f0b904.png)](https://chatthing.ai/blog/the-work-you-dont-see-and-why-it-makes-chat-thing-better) [<h4>The work you don't see (and why it makes Chat Thing better)</h4>](https://chatthing.ai/blog/the-work-you-dont-see-and-why-it-makes-chat-thing-better)

This month we rebuilt the engine room of Chat Thing. Not the bit you log into, but the part doing all the heavy lifting behind the scenes.. crawling your website, syncing your content from Notion, Google Drive and the rest, generating your analytics, sending your emails, running your agents' tasks. All of that runs on a separate system, and we tore it down and rebuilt it from scratch.

[![Lead Capture is live: meet your visitors before the first message](https://res.cloudinary.com/djyjvrw5u/image/upload/v1778228678/day_05_lead_capture_feature_card_v3_1920x1080_791009ded2.png)](https://chatthing.ai/blog/launch-week-05-lead-capture) [<h4>Lead Capture is live: meet your visitors before the first message</h4>](https://chatthing.ai/blog/launch-week-05-lead-capture)

Lead Capture is a native pre-chat form on the web channel. Visitors fill it in, the chat opens, and their answers flow into your systems via webhook so your assistant knows who it is talking to from message one.

<dl>

<dt>Previous</dt>
<dd>[← GPT-5.6 lands in Chat Thing, plus twelve more new models](https://chatthing.ai/blog/gpt-5-6-and-thirteen-new-models)</dd>

</dl>

## Footer

### Ready to answer every question, day or night?

Add an AI support agent to your site in minutes.

[Get started free](https://app.chatthing.ai/app/auth/register) [Book a demo](https://chatthing.ai/demo)

AI customer support that learns from your content and answers 24/7.

### Features

- [Channels: Deploy your bot](https://chatthing.ai/pages/features/channels)
- [Data sources: Add knowledge](https://chatthing.ai/pages/features/data-sources)
- [Power-ups: Tool calling](https://chatthing.ai/pages/features/power-ups)
- [AI Models: GPT-4, Claude, & more](https://chatthing.ai/pages/features/models)
- [SDK: Create custom assistants](https://chatthing.ai/pages/features/chatbot-sdk)
- [Bot evaluations: Test your bot](https://chatthing.ai/pages/features/testing)
- [Analytics: Topics, sentiment & insights](https://chatthing.ai/pages/features/analytics)
- [Bot Gallery: Example bots](https://chatthing.ai/gallery)
- [All features](https://chatthing.ai/features)

### Use cases

- [AI Customer Support Bots](https://chatthing.ai/pages/use-cases/customer-support)
- [AI Internal Knowledge Bots](https://chatthing.ai/pages/use-cases/internal-knowledge)
- [AI Bots for Marketing](https://chatthing.ai/pages/use-cases/marketing)
- [SDK: Create custom assistants](https://chatthing.ai/pages/features/chatbot-sdk)
- [All features](https://chatthing.ai/features)

### Channels

- [AI support for your website](https://chatthing.ai/pages/features/channels/website)
- [AI support for Slack](https://chatthing.ai/pages/features/channels/slack)
- [AI support for Discord](https://chatthing.ai/pages/features/channels/discord)
- [AI support for WhatsApp](https://chatthing.ai/pages/features/channels/whatsapp)
- [AI support for Telegram](https://chatthing.ai/pages/features/channels/telegram)
- [AI support API](https://chatthing.ai/pages/features/channels/api)

### Data sources

- [Chat with your website](https://chatthing.ai/pages/data-source/web)
- [Chat with your files](https://chatthing.ai/pages/data-source/files)
- [Notion chatbots](https://chatthing.ai/pages/data-source/notion)
- [Chat with your youtube](https://chatthing.ai/pages/data-source/youtube)
- [Chat with your RSS feed](https://chatthing.ai/pages/data-source/rss)

### Company

- [Discord](https://discord.com/invite/DGCCR34Fsj)
- [Docs](https://chatthing.ai/docs/getting-started)
- [Blog](https://chatthing.ai/blog)
- [FAQ](https://chatthing.ai/faq)
- [Status](https://status.chatthing.ai/)
- [Testimonials](https://senja.io/p/chat-thing/iq1tWz)
- [Custom AI development](https://chatthing.ai/pages/ai-development-services)

### Free tools

- [Agent Readiness Checker](https://chatthing.ai/tools/agent-readiness-checker)
- [JSON-LD Generator + Checker](https://chatthing.ai/tools/json-ld-generator)
- [llms.txt Generator & Validator](https://chatthing.ai/tools/llms-txt-generator)
- [Support Ticket Deflection Calculator](https://chatthing.ai/tools/ticket-deflection-calculator)
- [Knowledge Base Grader](https://chatthing.ai/tools/knowledge-base-grader)
- [AI FAQ Generator](https://chatthing.ai/tools/faq-generator)
- [AI Canned Response Generator](https://chatthing.ai/tools/canned-response-generator)
- [Support Bot Prompt Generator](https://chatthing.ai/tools/support-bot-prompt-generator)
- [All free tools](https://chatthing.ai/tools)

### Compare

- [Intercom alternative](https://chatthing.ai/pages/alternatives/intercom)
- [Zendesk alternative](https://chatthing.ai/pages/alternatives/zendesk)
- [Tidio alternative](https://chatthing.ai/pages/alternatives/tidio)
- [Crisp alternative](https://chatthing.ai/pages/alternatives/crisp)
- [Chatbase alternative](https://chatthing.ai/pages/alternatives/chatbase)
- [DocsBot alternative](https://chatthing.ai/pages/alternatives/docsbot)
- [ResolveAI alternative](https://chatthing.ai/pages/alternatives/resolveai)
- [ChatBotKit alternative](https://chatthing.ai/pages/alternatives/chatbotkit)
- [CustomGPT alternative](https://chatthing.ai/pages/alternatives/customgpt)
- [Botsonic alternative](https://chatthing.ai/pages/alternatives/botsonic)
- [Ada alternative](https://chatthing.ai/pages/alternatives/ada)

### Join our newsletter

Be the first to know about new features and updates.

Join

[Privacy](https://chatthing.ai/legal/privacy) [Terms](https://chatthing.ai/legal/terms) [DPA](https://chatthing.ai/legal/dpa) [GDPR](https://chatthing.ai/legal/gdpr) [Sub-Processors](https://chatthing.ai/legal/sub-processors)

[Twitter](https://twitter.com/pixelhopio) [Discord](https://discord.com/invite/DGCCR34Fsj) [YouTube](https://www.youtube.com/@ChatThingAI)

© 2026 Chat Thing. All rights reserved. Company number: 14789358. Built with  by [Pixelhop](https://pixelhop.io?utm_source=chat+thing&utm_medium=website)

## Cookies

We use cookies to run the site and understand how it's used. You can change your choice anytime.

Accept

Decline

Customise