AI agents like OpenClaw, ChatGPT, Claude, and Perplexity don't just search — they shop, book appointments, and compare services on behalf of users. If they can't read your site, you're invisible.
Join 1,000+ websites already scanned for AI agent readiness.
AI agent readiness measures how well a website can be accessed, read, and understood by autonomous AI systems like ChatGPT, Claude, and Perplexity. AgentSpeed scores this from 0 to 100 across 10 checks.
Why it matters to Website and Online Shop Owners
Here's what happens when an autonomous agent like OpenClaw, ChatGPT, or Claude tries to act on behalf of a user — and your website isn't ready.
Google AI Overviews, Perplexity, ChatGPT Search, Claude — users get answers from AI, not blue links. Autonomous agents like OpenClaw crawl websites to compare options and recommend the best match. If they can read your competitor but not you, the competitor wins.
Autonomous agents like OpenClaw are already comparing prices, checking availability, and booking flights on behalf of users. Soon they’ll browse apartments, order groceries, and pick insurance plans. Your product pages need structured data and accessible pricing.
“Book me a haircut for Saturday.” “Find a dentist this week.” “Reserve a table for four tonight.” Users delegate these tasks to agents like OpenClaw, ChatGPT, or Claude. If your flow needs JS interactions, the agent books your competitor instead.
Warranty claims, subscription changes, support questions — personal AI agents like OpenClaw handle these tasks autonomously. They need to understand your support pages and fill out your forms. Blocked or unreadable sites force users to do it manually.
The invisible problem
Your site looks fine in a browser. But AI agents see something different.
We value your privacy
This website uses cookies to ensure you get the best experience.
AI agents can't click “Accept”. Content stays hidden behind the overlay.
Designed to stop bots — and that includes the AI agents your customers send.
AI crawlers see empty HTML. Your pricing, features, menus — all invisible.
Sign in to continue
Agents don't have accounts. Content behind auth is completely unreachable.
Many sites copied “block all bots” rules without realizing AI crawlers are included.
Without schema markup, agents can't reliably extract prices, hours, or ratings.
Your score
AgentSpeed gives you a score from 0 to 100 — instantly understandable, with prioritized fixes for every issue found.
AI agents can fully access and understand your content
Some barriers are limiting agent access
Critical issues preventing agent interaction
Choose your scan
Start with the free scan for an instant overview, or go deep with a full audit across multiple pages.
Quick overview of your site's agent readiness
Full audit across multiple pages — like an agent sees your site
FAQ
An AI Agent Readiness score measures how well your website can be accessed, read, and understood by AI agents — from chatbots like ChatGPT, Claude, and Perplexity to autonomous agents like OpenClaw that browse, book, and buy on behalf of users. AgentSpeed runs 10 checks (13 with Deep Scan) covering access barriers, discoverability signals, and technical compatibility — then produces a score from 0 to 100 with prioritized fixes.
AI agents are becoming the primary way people interact with businesses online — not just for search, but for action. Chatbots like ChatGPT and Perplexity already recommend products and cite sources. Autonomous agents like OpenClaw go further: they browse websites, compare prices, book appointments, fill out forms, and manage subscriptions — all on behalf of users. If your site blocks AI crawlers, hides content behind JavaScript, or lacks structured data, these agents can’t read or interact with it — and users will go to a competitor whose site works.
The Free Basic Scan uses HTTP requests to check 10 factors in ~2 seconds — great for a quick overview. The Deep Scan (€29.90, one-time) simulates how an AI agent actually navigates your site: it scans up to 6 pages and runs 13 checks including 5 with higher accuracy (CAPTCHA detection, cookie wall analysis, JS dependency, login-wall detection, TTFB) plus 3 bonus checks (API documentation, MCP server, form accessibility).
The most common blockers are: (1) robots.txt rules that disallow AI crawlers like GPTBot or ClaudeBot, (2) cookie consent walls that require a click before showing content, (3) content that only renders with JavaScript execution, (4) missing llms.txt files, and (5) no structured data (Schema.org) for prices, products, or organization info. Most site owners don’t realize these issues exist because the site looks fine in a normal browser.
llms.txt is a proposed standard (like robots.txt but for AI) that provides a plain-text summary of your website optimized for large language models. It helps AI agents quickly understand what your site offers without crawling every page. While not yet universally adopted, having an llms.txt file at /llms.txt signals agent-friendliness and improves how AI systems understand your content.
PageSpeed Insights measures loading performance. Lighthouse audits accessibility and SEO basics. AgentSpeed measures something entirely different: whether AI agents — from chatbots (ChatGPT, Claude, Perplexity) to autonomous agents (OpenClaw) — can access and understand your content. It checks for AI-specific blockers like robots.txt rules for AI bots, cookie walls, CAPTCHA detection, llms.txt, structured data quality, and JavaScript dependency — none of which PageSpeed or Lighthouse test.
AgentSpeed checks your robots.txt for 16 AI bot user agents: GPTBot, ChatGPT-User, OAI-SearchBot (OpenAI), ClaudeBot, Claude-Web, anthropic-ai (Anthropic), PerplexityBot, Google-Extended, Applebot-Extended, CCBot, Bytespider, cohere-ai, Diffbot, FacebookBot, YouBot, and Amazonbot. These cover all major AI assistants and search engines that use AI crawlers.
Yes — the Free Basic Scan is completely free with no signup required. It runs 10 checks and gives you an instant score with actionable fix suggestions. The optional Deep Scan (€29.90, one-time payment) simulates how AI agents navigate your site across multiple pages with 13 checks for a more comprehensive assessment.
Enter any URL and get your AI Agent Readiness score in seconds. See what's blocking agents and get actionable fixes.