Skip to content
Is Agentic

anthropic.com

Ready with a few material gaps

77/ 100

Technical readiness score

What should the prompt cover?

16 findings · 5 selected

Failures (6)

Warnings (10)

How the score adds up

33 checks

The agent completed the observed task

One run shows how an agent performed, but it does not determine the technical score.

Task

What does anthropic.com do and who is it for? Explain it back to me.

17 steps3 reasoning steps3 searches

home
/research
docs
/product
docs
/papers
/api
docs
docs
/careers
search
docs
search
search
1 observed runView journey ↗

Critical access needs attention

These checks describe whether an ordinary agent can enter, read, and operate the public site.

  • Agents can reach the site

    Crawler access, bot defenses, and explicit agent policy.

    3 / 3 passed

  • Core content is available

    Useful content remains accessible without a fragile browser-only path.

    1 / 2 passed

  • Navigation fails safely

    Redirects and missing pages give agents a recoverable path.

    1 / 2 passed

  • Controls are understandable

    Forms and interactive controls expose usable names and structure.

    3 / 3 passed

Advertised capabilities have material gaps

Optional surfaces appear only when the scan finds positive evidence that the site offers them.

Public website

Ready with gaps

70%

10 of 19 mature checks passed

API

Needs work

63%

5 of 9 mature checks passed

Authentication

Strong

87%

2 of 3 mature checks passed

MCP

Blocked

42%

0 of 2 mature checks passed

Fix these gaps first

Critical access gaps come first, followed by gaps in capabilities the site advertises.

  1. 01

    Content without JavaScript

    Server-side render your homepage so AI crawlers see meaningful content without JavaScript. Ensure an H1 and 500+ chars of text in raw HTML.

    Critical access
  2. 02

    Agent-friendly 404s

    Return a real HTTP 404 (or 410) status for nonexistent paths - never a 200 with your app shell, which makes agents believe every path exists. For full credit, give the 404 response a short markdown body pointing agents at your sitemap, llms.txt, or docs index. Verify with `curl -s -o /dev/null -w "%{http_code}" https://yourdomain.com/some-path-that-does-not-exist` - it must print 404.

    Critical access
  3. 03

    OpenAPI spec published

    Publish an OpenAPI (Swagger) specification at /openapi.json or /api/openapi.yaml. This is how agents understand your API surface automatically.

    Advertised capabilities
  4. 04

    OAuth 2.0 support

    Implement OAuth 2.0 for API authentication. Publish your authorization server metadata at /.well-known/oauth-authorization-server.

    Advertised capabilities
  5. 05

    MCP Apps support

    Add MCP Apps support to your MCP server using @modelcontextprotocol/ext-apps. Expose ui:// resources and add _meta.ui.resourceUri to tools so agents can render interactive UIs directly in conversation.

    Advertised capabilities

Audit the checks behind the score

Applicable evidence is grouped by how it contributes to this preview model. Bonus checks appear only when they add points.

Essential7 of 11 passed · 61.3 / 80 points
  • Content without JavaScriptPartial (33%)
  • Not blocked by bot detectionPassed
  • robots.txt agent-user policyPassed
  • Redirect hygienePassed
  • Content behind authPassed
  • OpenAPI spec publishedFailed
  • Agent crawler reachabilityPassed
  • OAuth 2.0 supportPartial (60%)
  • Scoped permissionsPassed
  • JSON error responsesPassed
  • Agent-friendly 404sPartial (50%)
Recommended10 of 22 passed · 12.7 / 20 points
  • Developer resource discoverabilityPartial (33%)
  • Brand name discoverabilityPassed
  • robots.txt AI crawler policyPartial (50%)
  • Sitemap existsPassed
  • Content efficiencyPartial (50%)
  • JSON-LD structured dataFailed
  • Public API/docs linked from homepagePassed
  • Agent instruction / when-to-usePartial (67%)
  • Metadata completenessPassed
  • Organization schema completenessFailed
  • Trust anchor pagesPartial (50%)
  • Page token budgetPassed
  • Code fence validityPassed
  • Developer portalPassed
  • Public API with reachable endpointsPassed
  • Agent onboarding frictionPassed
  • MCP server / manifestPartial (83%)
  • CLI tool availablePartial (67%)
  • Multi-language SDK packagesPassed
  • MCP Apps supportFailed
  • API schema complexity analysisFailed
  • Function calling compatibilityFailed
Bonus signals14 positive · +3.3 points
  • NPM/PyPI SDK packagePassed
  • Agent platform configsPassed
  • Listed on skills.shPassed
  • MCP well-known discoveryPartial (50%)
  • Sitemap freshness (lastmod)Passed
  • llms.txt existsPassed
  • llms.txt formattingPartial (50%)
  • Skills.sh skill qualityPassed
  • llms.txt links resolvePassed
  • Native interactive controlsPassed
  • Accessible names on controlsPassed
  • Form control labelingPassed
  • Accessibility-tree injection safety (bonus)Passed
  • A2UI / generative UI supportPassed

Inspect the underlying audit

The complete Ora audit uses evidence from the scan on . After applying changes, run another scan from the homepage to refresh these recommendations.

Score alerts

A weekly report with ranking changes, new agent feedback, and score alerts for anthropic.com.

Source: Ora API

Snapshot 2026-08-15T00-00-55-431+00-00