Vercel releases Is Agentic to score website readiness
Vercel has launched Is Agentic, a free tool that audits how easily AI agents can navigate and use public websites, helping developers optimize their platforms for the agentic web.

Vercel has introduced Is Agentic, a free public tool designed to evaluate how effectively artificial intelligence agents can discover, access, understand, and interact with websites. Powered by 118 checks developed by agent-experience research firm Ora, the tool requires no API keys, subscription fees, or billing accounts. Developers can access the service through a web browser, a command-line interface, a read-only API, or a Model Context Protocol (MCP) server.
The underlying methodology from Ora evaluates websites across four distinct layers: discovery (worth 20 points across 15 checks), access (30 points across 41 checks), usability (40 points across 56 checks), and payments (10 points across 6 checks). While Ora uses a letter grade scale from A+ down to F, Vercel maps these audits to its own scoring system. This system allocates an 80-point pool for essential checks, a 20-point pool for recommended checks, and up to 5 bonus points for emerging signals. Non-applicable checks are excluded so that simpler marketing sites are not penalized for lacking complex features like API endpoints.
For practitioners, the tool provides actionable insights to prevent agent friction. Audits include specific check identifiers such as content-no-js, agent-friendly-404, and markdown-negotiation-vary. The API, located at /api/v1/report, is rate-limited to 120 requests per client IP every 60 seconds. Developers can also integrate the tool directly into continuous integration pipelines to fail builds if server-rendered content regresses, or install an official agent skill using the command 'npx skills add vercel-labs/is-agentic'.
Vercel emphasizes that Is Agentic is designed as a prioritized technical review rather than a formal security audit, accessibility review, or certification. By converting recommendations into copy-pasteable prompts, developers can quickly direct coding agents to resolve discovered issues, ensuring their public web surfaces remain highly navigable as autonomous AI agents become more prevalent.
This is our own summary of reporting by MarkTechPost


