Finalizing the report
Preparing the stored Is Agentic score
Essential—
Recommended—
Bonus signals—
Preparing the stored Is Agentic score
claude.ai
These checks describe whether an ordinary agent can enter, read, and operate the public site.
Agents can reach the site
Crawler access and bot defenses.
Core content is available
Useful content remains accessible without a fragile browser-only path.
The public website is always evaluated. Optional surfaces appear when the scan finds positive evidence that they apply.
Blocked
Weighted across 12 applicable checks
Blocked
Weighted across 9 applicable checks
Critical access gaps come first, followed by other applicable readiness gaps.
Serve at least 500 characters of meaningful homepage content in raw HTML. Add a clear H1, keep deeper heading levels sequential, and remove excessive non-content markup.
Allowlist known AI agent User-Agents (ChatGPT-User, ClaudeBot, Google-Extended, DeepSeekBot) in your WAF or bot-detection rules.
Verify that major agent User-Agents can reach the homepage. If your WAF or bot rules block them, remove or narrow the blocking rule. Add an allow rule only when your security setup denies them by default.
Enable Markdown negotiation on the scanned homepage. Supporting it only on /docs or a separate .md URL does not satisfy this check. Requests with Accept: text/markdown must receive a nonempty Markdown body with Content-Type: text/markdown and Vary: Accept. Keep serving HTML for Accept: text/html. Adding Vary alone does not create a Markdown response. Verify both with curl -sS -L -i -H 'Accept: text/markdown' https://yourdomain.com/ and curl -sS -L -i -H 'Accept: text/html' https://yourdomain.com/. Check the final response headers and body: Markdown with Vary: Accept for the first request, HTML for the second.
Add JSON-LD structured data to your homepage using the identity type that matches your site - SoftwareApplication for products, Organization or LocalBusiness for companies, Person for personal sites, Article for blogs - with name, description, url, and type-appropriate fields (offers, sameAs, author) so AI can parse your identity programmatically.
Checks are grouped by relevance for Docs & content sites.
Homepage blocked by WAF/security challenge - content not accessible to agents
How to pass
Serve at least 500 characters of meaningful homepage content in raw HTML. Add a clear H1, keep deeper heading levels sequential, and remove excessive non-content markup.
Bot management challenged GPTBot, ClaudeBot, ChatGPT-User, PerplexityBot, Google-Extended, Applebot-Extended. A challenge is an identity check that verified crawlers pass, so this is not proof agents are blocked - but unverified agents will not get through.
How to pass
Allowlist known AI agent User-Agents (ChatGPT-User, ClaudeBot, Google-Extended, DeepSeekBot) in your WAF or bot-detection rules.
Homepage https://claude.ai does not meet the Markdown negotiation requirements: Accept: text/markdown returned text/html; charset=utf-8; Vary header missing Accept (got "accept-encoding")
How to pass
Enable Markdown negotiation on the scanned homepage. Supporting it only on /docs or a separate .md URL does not satisfy this check. Requests with Accept: text/markdown must receive a nonempty Markdown body with Content-Type: text/markdown and Vary: Accept. Keep serving HTML for Accept: text/html. Adding Vary alone does not create a Markdown response. Verify both with curl -sS -L -i -H 'Accept: text/markdown' https://yourdomain.com/ and curl -sS -L -i -H 'Accept: text/html' https://yourdomain.com/. Check the final response headers and body: Markdown with Vary: Accept for the first request, HTML for the second.
Bot management challenged ChatGPT-User, ClaudeBot, Google-Extended, ora-agent, DeepSeekBot - a challenge is an identity check verified crawlers pass, so reachability is undetermined rather than blocked (ChatGPT-User: challenged, ClaudeBot: challenged, Google-Extended: challenged, ora-agent: challenged, DeepSeekBot: challenged)
How to pass
Verify that major agent User-Agents can reach the homepage. If your WAF or bot rules block them, remove or narrow the blocking rule. Add an allow rule only when your security setup denies them by default.
No sitemap found
How to pass
Add a valid XML sitemap at /sitemap.xml listing all indexable URLs. Include lastmod dates and keep it under 50MB.
Homepage blocked by WAF - cannot check structured data
How to pass
Add JSON-LD structured data to your homepage using the identity type that matches your site - SoftwareApplication for products, Organization or LocalBusiness for companies, Person for personal sites, Article for blogs - with name, description, url, and type-appropriate fields (offers, sameAs, author) so AI can parse your identity programmatically.
Homepage blocked by WAF - cannot check metadata
How to pass
Add all four signals to your homepage: , , , and . Agents use these for entity resolution and attribution.
No trust anchor pages found with sufficient content (About, Contact, Privacy)
How to pass
Publish real /about, /contact, and /privacy pages with at least 500 characters of content each. These are the pages AI agents check to verify your business is legitimate before recommending you.
claude.ai appears once in brand-name search results for "claude ai ml" (position #8 out of 9)
How to pass
Make sure a clean search for your brand name returns your own domain in the top results. If it does not, your brand may be too generic, conflict with a more established term, or not yet indexed. Strengthen brand-name search by claiming consistent NAP across listings, earning press mentions that link to the canonical domain, and avoiding redirect chains that mask the apex domain in search results.
Wikidata Q118876059 (Claude) verified - draft a Wikipedia page with cited references to complete knowledge graph coverage
How to pass
Establish a Wikipedia article and a Wikidata entity for your brand, with the domain set as the official website (Wikidata property P856) and a corresponding external link on Wikipedia. Wikipedia is the largest single source of citations in ChatGPT and a primary input to Knowledge Graphs across Google, Bing, and LLM training data. Earn third-party press coverage first to satisfy notability, then draft the article with cited references rather than self-promotion.
Agent rules repo found: github.com/KazuoMurakami/rules-skills-agents-claude
4 official skills published on skills.sh - 46,763 total installs (skills.sh/claude-office-skills)
Agent instruction file at /agent.txt but no explicit when-to-use guidance
How to pass
Tell agents when to reach for you: add a 'when to use this' section to your llms.txt (or a dedicated agent-instructions file) that names your best-fit use cases and how an agent should call you. Be specific about the jobs you are right for - generic marketing copy does not read as guidance.
Skills.sh presence exists but limited - 4 skills (goal: 5+)
How to pass
Expand your skills.sh presence with multiple skill repos covering different use cases. Add descriptive skill names, clear SKILL.md files, and organize by capability area.
GraphQL endpoint at https://claude.ai/graphql is reachable; introspection requires authentication (API key / OAuth), which is expected for agent access. Best-of-protocols score: 7/7.
NLWeb /ask endpoint exists but requires authentication (HTTP 403, via GET)
What does claude.ai do and who is it for? Explain it back to me.
Sign me up for Vercel product updates and marketing emails.
Unsubscribe anytime. Privacy Notice
Source: Ora API
What does claude.ai do and who is it for? Explain it back to me.
13 steps6 reasoning steps3 searches
The agent successfully assembled a comprehensive explanation of Claude.ai by working around direct access blocks to the main domain and relying on web search plus third-party documentation. The primary claude.ai website (claude.ai/) was inaccessible via Cloudflare challenge, forcing the agent to pivot to claude.com pricing pages, Anthropic's main site, and platform documentation—all of which were fetchable. The agent delivered a complete answer covering what Claude does, who it's for, pricing tiers, and competitive differentiation, but acknowledged gaps in specific details (exact free tier limits, real customer use cases) that the site did not transparently surface.