--- title: Vercel Shipped is-agentic.com. Here Is How the Scoreboard Works dek: >- Ora runs the checks. Vercel publishes the report. The CLI, the markdown URL, and the MCP server are how an agent uses the grader on itself. slug: vercel-shipped-is-agentic publishedAt: '2026-08-21' author: agnel-nieves pillar: aeo-visibility tags: - aeo - is-agentic - agents - vercel - ora - mcp summary: >- is-agentic.com is Vercel's public scoreboard for whether AI agents can discover, read, and use a website. Ora runs the audit. The score is applicability-aware: essential checks share 80 points, recommended share 20, and a bonus cap of 5 never becomes a requirement. The product is itself agentic: a CLI, Accept: text/markdown, a JSON report API, and a read-only MCP server. draft: false featured: false heroImage: /blog/vercel-shipped-is-agentic.webp heroImageAlt: >- Engraved illustration of a gold inspector's stamp, its face a greater-than glyph, resting on a certificate beside ledgers, an abacus, and a spilled inkwell, framed by botanicals on a kelly green ground. heroVideo: /blog/vercel-shipped-is-agentic.mp4 ogImage: /blog/vercel-shipped-is-agentic-og.jpg assetCredit: Hero illustration and animation generated with Grok. audioEn: /blog/vercel-shipped-is-agentic.en.mp3 audioDurationSeconds: 360 audioCredit: Synthesized via Kokoro (am_puck). --- Vercel shipped a public score for whether agents can read your site. I had already been doing this work by hand on Promptway: llms.txt, feeds, JSON-LD, markdown siblings, an allowlist in robots.txt. Then they put a number on it and a CLI behind it, which is the part I wanted. The announcement is from [@vercel_dev](https://x.com/vercel_dev), August 20, 2026. ```tweet https://x.com/vercel_dev/status/2090857388924661915 Introducing is-agentic.com, a tool to measure how well agents can read your site. Backed by @oradotai's research, you can run: Audits with 100+ checks Visualizations of agents using your site One-click prompts to fix problems A CLI for agents ``` [is-agentic.com](https://is-agentic.com) is the report. [Ora](https://ora.ai) is the scanner. That split is load-bearing. Ora runs every check and scores each layer. Vercel groups those results into Essential, Recommended, and Bonus, stores the history, and publishes a shareable page. If you argue with a number, you are arguing with Ora's evidence first and Vercel's grouping second. The [about page](https://is-agentic.com/about) is honest about the limits: a score is a public snapshot, not a certification. Automated checks can be wrong. Read the evidence. ## What the number is The [methodology](https://is-agentic.com/methodology) is short. Read it before you treat 74 or 91 as a grade on your company. Essential checks share an 80-point pool. Recommended checks share 20. Emerging signals can add a bonus, capped at five, and their absence never lowers the score. Partial results get proportional credit. Checks that do not apply are excluded. That last rule is the one I care about. A publication is not penalized for missing OAuth. A SaaS is not scored as a brochure. API, GraphQL, MCP, and commerce checks only fire when the scan finds that surface. Duplicated check IDs across MCP surfaces are averaged so you do not get double-counted for the same gap. Start with failed Essential items. Those are the things that stop an ordinary agent: wrong status codes, HTML that is an empty shell, errors that look like pages, content that only exists after JavaScript. Recommended items are for the product you actually ship. Bonus is gravy. Each report also shows an observed agent journey. One agent, one walk through the site, the places it got stuck. That run is not part of the numeric score. One task is not a sample of every agent. Treat it as a clip, not a study. Reports cache. A re-scan minutes after a deploy can hand you the old number. Give it about six hours, or wait until the snapshot timestamp moves. ## The grader is a client of itself Chris Tate, who works on this at Vercel, posted the joke the same day. ```tweet https://x.com/ctatedev/status/2090865331862446088 Best part: is-agentic.com is itself agentic Your agent can use it to make your site more agentic ``` That is not branding. The [docs](https://is-agentic.com/docs) describe a stack that looks like the checklist they grade you on. The CLI is on npm as [`is-agentic`](https://www.npmjs.com/package/is-agentic): ```sh npx is-agentic promptway.com npx is-agentic promptway.com --json ``` It returns a stored report if one exists, or starts a scan and waits. `--json` is the unchanged API body, including structured errors. That is the shape you hand an agent if you want it to close the loop without scraping a HTML report. Public pages speak markdown. Send `Accept: text/markdown` at the same URL that serves HTML and you get `Content-Type: text/markdown; charset=utf-8` with `Vary: Accept`. If the client rejects every representation they produce, they 406. The HTML report is complete in the first response, so a crawler does not have to run JavaScript to see the score. The report API is `GET https://is-agentic.com/api/v1/report?url=...`. No auth. Errors use RFC 9457 `application/problem+json`. It does not start a new scan. 404 means nothing is stored yet; start one from the site. Rate limit is 120 requests per IP per 60 seconds, with IETF `RateLimit` headers. OpenAPI lives at [is-agentic.com/openapi.json](https://is-agentic.com/openapi.json). The RFC 9727 catalog is at [/.well-known/api-catalog](https://is-agentic.com/.well-known/api-catalog). There is a read-only MCP server at [https://is-agentic.com/mcp](https://is-agentic.com/mcp). Three tools: `is_agentic_get_report`, `is_agentic_get_methodology`, `is_agentic_get_developer_docs`. No OAuth, no API key. Registry metadata is at [server.json](https://is-agentic.com/server.json). Hosts that support MCP Apps can render `ui://is-agentic/score-report.html`. It is free. [pricing.md](https://is-agentic.com/pricing.md) is a machine-readable statement, not a pricing page with a toggle. No write APIs, no webhooks, no keys. You run a scan in the browser. Everything else is read. ## How I would use it Run the CLI once. Read Essential failures against a live `curl` before you edit anything. Soft 404s and missing `Vary` headers are easy to misread from source. Then hand the report's fix-it prompt to whatever coding agent you use, with one extra instruction: do not invent product surface to chase Recommended or Bonus. If you do not run an MCP server, do not publish a fake one. If you are a publication, document the machine-readable content stack and stop. The applicability model only works if you refuse the checks that are not yours. I pointed it at this host and wrote the field report separately: [is-agentic Scored Promptway 74. Here Is What I Changed](/blog/is-agentic-scored-promptway-74). That piece is the 74, the diffs, and the prompt I would reuse. This piece is the product. ## What this writeup does not cover I am not reciting Ora's full check list. They own that, and it will move. I am not treating a score as an accessibility audit, a security review, or a ranking guarantee. The about page already said so. I also have not waited out the cache on Promptway's production rescan. The number I have is the one from before we shipped the 74-post fixes. When the snapshot timestamp moves, that field report is the place to look. If you only read one page besides this one, make it the [methodology](https://is-agentic.com/methodology). Then run the CLI on your own host. ## Sources - [is-agentic.com](https://is-agentic.com) - [is-agentic about](https://is-agentic.com/about) - [is-agentic methodology](https://is-agentic.com/methodology) - [is-agentic docs](https://is-agentic.com/docs) - [is-agentic OpenAPI](https://is-agentic.com/openapi.json) - [is-agentic MCP](https://is-agentic.com/mcp) - [Ora](https://ora.ai) - [Vercel announcement](https://x.com/vercel_dev/status/2090857388924661915) - [Chris Tate on the product being agentic](https://x.com/ctatedev/status/2090865331862446088) - [is-agentic Scored Promptway 74. Here Is What I Changed](/blog/is-agentic-scored-promptway-74) - [I fixed my site for agents by hand. Then Vercel shipped a scoreboard](https://agnelnieves.com/blog/measuring-how-agentic-my-site-is-with-is-agentic.md)