---
title: Agent Readability Score
description: Score any website against the Vercel Agent Readability Spec. 38 checks across discovery, structure, and context for AI agents.
last_updated: 2026-05-11
canonical_url: https://agent-ready.dev/agent-readability-score
---

# Agent Readability Score

> Score any website against the Vercel Agent Readability Spec. 38 checks across discovery, structure, and context for AI agents — produces a 0–100 score with rating bands.

## Why does the Vercel Agent Readability Score matter?

ChatGPT, Claude, and Perplexity don't have Google's 25 years of webmaster lineage — they crawl what loads cleanly and cite what parses correctly. A [Pew Research study (July 2025)](https://www.pewresearch.org/short-reads/2025/07/22/google-users-are-less-likely-to-click-on-links-when-an-ai-summary-appears-in-the-results/) found Google users clicked on source links only about 8% of the time when an AI summary appeared, roughly half the rate without one. Princeton's [GEO research (KDD 2024)](https://arxiv.org/abs/2311.09735) measured that adding cited sources and statistics can lift a page's inclusion in AI answers by about 40%.

## How is the agent readability score calculated?

`score = round((passed checks / total checks) × 100)`. Per-page checks run on every discovered page, so systemic issues compound: 15 site-wide checks plus (23 per-page × number of pages scanned).

## What do the score ratings mean?

- **90–100** Excellent — completely optimized for AI execution.
- **70–89** Good — complies with key properties; minor warnings.
- **50–69** Fair — significant architectural gaps.
- **0–49** Needs Improvement — unreliable for machine operations.

## What does the agent readability scanner check?

**15 site-wide checks (S1–S15):** llms.txt presence and validity, robots.txt allowlist for AI crawlers, sitemap.xml validity, sitemap.md presence, AGENTS.md or equivalent skill file, HTTPS, OpenAPI spec for API-first sites.

**23 per-page checks (P1–P23):** HTTP status, redirect chain length, Content-Type, x-robots-tag, canonical link, meta description, og:title/og:description, html lang, JSON-LD presence and required fields, heading structure, text-to-HTML ratio, markdown mirrors, content negotiation, code-block language tags, JS-rendering dependency.

## How do I improve my score?

Every failed check on a scan result comes with a concrete fix — what file to add, what header to set, what markup to emit. Work top-down: site-wide issues (llms.txt, robots.txt, sitemap) compound across every page and are usually the highest-leverage thing to fix first.

## Specification

- [Vercel Agent Readability Spec](https://vercel.com/kb/guide/agent-readability-spec)
- [Vercel "Make your documentation readable by AI agents"](https://vercel.com/kb/guide/make-your-documentation-readable-by-ai-agents)

---

Run the scanner: <https://agent-ready.dev/agent-readability-score>

## Sitemap

See the full [sitemap](https://agent-ready.dev/sitemap.md) for all pages on agent-ready.dev.