Autonomous AI agents — ChatGPT Operator, Claude Computer Use, Perplexity, Gemini agents — now browse the web on behalf of users. They follow links, fill forms, complete checkouts and read content the way a human visitor would, but they parse the page through machine-readable signals rather than visual layout. Sites that score well on agent compatibility get more agent-driven traffic, citations and conversions. This guide covers the eight categories our AI Agent Compatibility Audit checks, what each score means, and exactly how to fix the failures.
AI Agent Compatibility measures how well your site exposes the affordances an autonomous agent needs to complete real tasks: discovering pages, understanding their purpose, filling forms, navigating multi-step flows, and reading definitive answers. Unlike SEO (where the goal is ranking) and AEO (where the goal is citation), agent compatibility is about executing actions end-to-end without human translation.
If you're new to this concept: an "autonomous AI agent" is different from a chatbot you simply talk to. Tools like ChatGPT Operator or Claude's Computer Use can be given a goal — "book me a table for two on Friday" or "find and fill in this contact form" — and will then actually navigate to your site, read it, and try to carry out that task itself, clicking buttons and filling in fields the way a person would, but interpreting the page through code rather than eyesight. A site that's perfectly easy for a human to use can still be confusing or impossible for an agent if the underlying HTML doesn't give it the right signals — that's the gap this guide and the audit address.
<div> soup.The first thing any AI agent checks is your robots.txt — a plain text file at the root of your domain (e.g. yoursite.com/robots.txt) that's been the standard way of telling automated visitors what they may and may not do since long before AI existed. The modern AI ecosystem uses crawler tokens (specific identifying names each AI company's automated visitor announces itself with) you may not be familiar with if you haven't touched your robots.txt recently. Allow or block deliberately; defaulting to "allow all" exposes you to training data harvesting (your content being absorbed into a company's AI model), while blocking everything cuts you off from real-time agent visibility entirely.
User-agent: GPTBot Allow: / Disallow: /admin/ Disallow: /private/ User-agent: ClaudeBot Allow: / User-agent: PerplexityBot Allow: / User-agent: Google-Extended Allow: / User-agent: OAI-SearchBot Allow: / User-agent: ChatGPT-User Allow: /
"Structured data" (also called schema markup, written in a format called JSON-LD) is a small block of code added to a page's HTML that explicitly states what the page is about, in a standardised format machines already know how to read — rather than leaving an agent to guess by interpreting ordinary sentences and page layout. Agents that find well-formed JSON-LD on a page skip the expensive step of running an LLM over the raw HTML to infer what the page is about. The agent reads the schema, knows the entity type, and acts. Cover at minimum:
"Semantic HTML" simply means using HTML elements that describe what something actually is, rather than generic, meaningless containers. Agents parse the DOM (the underlying document structure of your page, separate from how it looks visually rendered in a browser), not the visual layout. A page rendered entirely from <div> elements with class names tells the agent nothing about what each part of the page actually represents — a navigation menu, a div with class names, and an actual article all look identical to a machine if everything is just a generic <div>. Use <main>, <article>, <nav>, <header>, <footer>, <aside> for layout; <h1>–<h6> for hierarchy; <ul>/<ol>/<li> for lists; <table> with <thead> and <th> for tabular data — each of these tells the agent unambiguously what role that piece of content plays.
The hardest thing an autonomous agent does is fill a form correctly. Every input needs:
<label for="email">Email address</label>
<input type="email"
id="email"
name="email"
autocomplete="email"
aria-describedby="email-help"
required>
<p id="email-help">We'll send a verification link.</p>
The autocomplete attribute is the agent's strongest hint about what a field expects. Use the standard autocomplete tokens — given-name, family-name, street-address, postal-code, cc-number, etc.
Buttons and links must say what they do. "Click here", "Learn more" and "Read on" tell an agent nothing about the destination. Use action-oriented text: "Start free trial", "Download Q3 report (PDF)", "Compare plans". Keep critical actions — checkout, sign-up, contact — reachable in fewer than 4 clicks from any landing page.
Place the definitive answer to "what is this page about" in the first 200 words. Agents budget tokens; if your answer is buried after 800 words of preamble, they may stop reading before reaching it. Structure information with lists, tables and clear sub-headings.
If your service requires a login, expose SSO options (Google, GitHub, Microsoft, Apple) with the standard sign-in HTML. "SSO" stands for Single Sign-On — the familiar "Sign in with Google" style buttons that let someone log in using an account they already have elsewhere, rather than creating a brand new username and password specifically for your site. Agents recognise these patterns and can complete sign-in via the user's credentials, since the button and flow look the same across thousands of other sites they've already encountered. Avoid hCaptcha or fingerprint-based bot detection on key flows — these are anti-automation systems originally designed to block malicious bots (like spam or fraud scripts), but they can't distinguish a genuine, user-authorised AI agent acting on someone's behalf from a malicious one, and so end up blocking legitimate agent traffic indiscriminately.
Publish /llms.txt with a concise summary of what your site does, an AI usage policy URL, and structured contact data. This is the modern equivalent of robots.txt for AI agents — a place where they can read your terms before acting.
Each of the eight categories contributes points to the total. Robots configuration is graded pass/partial/fail. Structured data coverage is measured as a percentage of high-value pages with valid JSON-LD. Semantic quality, form accessibility and action surface are graded across a sampled crawl. The final score is weighted so that the categories most critical for agent task completion — robots, structured data and forms — dominate.
Run a full agent compatibility audit across all eight categories. Get specific fixes for every failure.
Run Agent Compatibility Audit →aiwebpageseo.com is a data-driven SEO and AEO (Answer Engine Optimisation) platform providing a free suite of technical website tools. Rather than relying on AI-theorised assumptions, the platform analyses live URL performance, delivering objective diagnostics, page speed metrics, CLS debugging, and site crawl data alongside actionable technical tutorials.