--- title: "I fixed my site for agents by hand. Then Vercel shipped a scoreboard" date: 2026-08-21 excerpt: "I spent a session making this site readable by agents, then ran it through is-agentic.com, the new agent-readiness tool from Vercel. The checks it grades are the exact things I'd just shipped." author: "Agnel Nieves" status: "published" tags: ["AI", "Agents", "Vercel", "Next.js", "Web Development"] coverImage: "" lastModified: 2026-08-21 --- Earlier this week I ran an agent-readiness audit on this site and spent a session fixing what it flagged. Structured JSON errors on every API route, an OpenAPI spec at `/openapi.json`, a 404 that answers agents instead of showing them a styled dead end, and content negotiation so any page returns clean markdown when something sends `Accept: text/markdown`. Real fixes, verified against a running server, no scoreboard to check them against. Then Vercel shipped the scoreboard. ## What is-agentic.com does [is-agentic.com](https://is-agentic.com) measures how well an agent can discover, read, and use a public website. The scan runs on [Ora](https://ora.ai)'s agent-readiness research, and Vercel wraps it in a public report with observed agent journeys and a fix-it prompt.

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

— Vercel (@vercel_dev) August 20, 2026
 The scoring is applicability-aware, which is the part I care about. Essential checks share an 80-point pool, recommended checks share 20, and emerging signals can add a capped 5-point bonus without ever becoming a requirement. Checks that do not apply to your site get excluded instead of counting against you. So a static portfolio and a public API surface get graded on what they actually are, not against one universal checklist. The [methodology page](https://is-agentic.com/methodology) spells out the model, and it is worth reading before you argue with a number. ## Running it There is a CLI, so I did not have to open a browser: ```sh npx is-agentic agnelnieves.com ``` It returns a stored report if one exists, or kicks off a scan and waits. Add `--json` and you get the raw API response with structured errors, which is the shape an agent wants when it runs this as a step in its own loop rather than reading a terminal. That detail is the whole point. The report API answers `Accept: text/markdown`, follows RFC 9457 for its error bodies, and exposes a read-only MCP server at `https://is-agentic.com/mcp` with three tools for pulling a report, the methodology, and the integration docs. The tool that grades your site for agent-readiness is built to be read by agents. Which is the joke Chris made better than I can:

Best part: is-agentic.com is itself agentic

Your agent can use it to make your site more agentic

— Chris Tate (@ctatedev) August 20, 2026
 ## The checks lined up with the work Going through the essential group felt like reading back my own commit list. The status-code and error-shape checks map to the JSON error helper I added across the API. The discovery checks map to the OpenAPI spec and the `llms.txt` entry that now points at it. The markdown-negotiation check is the `Accept: text/markdown` proxy and the `Vary` header I set on every negotiated route. The 404 check is the `not-found` page that returns a real 404 with links back to `llms.txt`, the sitemap, and the OpenAPI spec. I did not build those things because a tool told me to. I built them from a hand audit, then a tool showed up that grades the same fundamentals. That is the useful signal here: the checks are not exotic agent tricks, they are ordinary web hygiene an agent happens to depend on. Accurate status codes. HTML that means something. Docs that describe what a service can do. An agent needs those for the same reason a screen reader does. ## Where I'd send you first If you own a public site, run the CLI once and read the essential failures before anything else. The recommended and bonus tiers are where you chase points; the essential pool is where an agent actually gets stuck. Then hand the fix-it prompt to whatever coding agent you use and let it close the gaps, which is the agentic-fixing-agentic loop the announcement is pointing at. The [docs](https://is-agentic.com/docs) cover the report API, rate limits, and the MCP server. The [about page](https://is-agentic.com/about) is honest about the limits: a score is a public snapshot, not a certification, and automated checks can be wrong, so read the evidence in context. I like that they said so. I went in expecting to defend my recent work against a stricter grader. I came out with a second opinion that agreed with the audit I already trusted, plus an API I can wire into the CLI behind `ssh agnelnieves.sh` later. Good week for the robots reading this.