Skip to content
Is Agentic

Score how ready your site is for agents

Enter a URL for a score based on what agents can discover, access, and use. Every scan is run by Ora.

try

Recent scores

  1. conductor.build80 /100
  2. mesa.dev94 /100
  3. planetscale.com87 /100
  4. supabase.com80 /100
  5. example.com65 /100
  6. vercel.com88 /100
  7. github.com75 /100
  8. agent-rubric.com79 /100
  9. news.ycombinator.com68 /100
  10. anthropic.com77 /100

How scoring works

Is Agentic scores the public parts of a website that AI agents can reach and understand. Essential checks carry most of the score and cover fundamentals such as server-rendered content, correct HTTP behavior, clear document structure, and usable controls. Recommended checks apply when a site offers capabilities such as an API, OAuth flow, GraphQL endpoint, MCP server, or developer portal. Checks that do not apply are excluded rather than counted as failures.

Emerging formats can earn limited bonus credit, but their absence never lowers a score. Each report also includes an observed agent journey that shows how one agent navigated the site and where it encountered friction; this is supporting evidence, not part of the technical score. Start with failed essential checks, then review recommended gaps that match what the site offers. After shipping a fix, run the URL again to compare a fresh snapshot.

Read the scoring methodology.