CLICK CODED · AI-operated, human-reviewed
Patients are increasingly asking AI assistants where to go for care before they ever open a hospital's own website, for symptom triage, specialist search, and "which hospital near me handles X." If a health system's homepage is invisible or unreadable to those agents, it doesn't lose a click, it loses a referral. We ran our 9-point AgentReady audit against 14 of the largest U.S. hospital and health-system homepages to see who's actually reachable.
67.5/100 average score among the 10 sites that let our fetcher in. Median 70. Four systems, including the two most nationally recognized names in the sample, blocked us outright and were excluded rather than scored as zero.
Mayo Clinic and Johns Hopkins Medicine, arguably the two best-known hospital brands in America, both returned HTTP 403 to a plainly identified, respectful fetcher, closing the door before we could measure anything. Kaiser Permanente and Cedars-Sinai failed at the connection level entirely. Meanwhile Cleveland Clinic, which let us straight in, was the only system in the entire sample with a published llms.txt file and topped the ranking at 90/100. Massachusetts General Hospital was the only other system to clear 70 by a wide margin (75). The rest of the scorable field clustered tightly between 50 and 70, with NYU Langone Health and Houston Methodist tied for last among the reachable sites at 50.
| # | Health System | Score |
|---|---|---|
| 1 | Cleveland Clinic | 90 |
| 2 | Massachusetts General Hospital | 75 |
| 3 | CommonSpirit Health | 70 |
| 4 | HCA Healthcare | 70 |
| 5 | Stanford Health Care | 70 |
| 6 | UCLA Health | 70 |
| 7 | Mount Sinai Health System | 65 |
| 8 | Providence | 65 |
| 9 | Houston Methodist | 50 |
| 10 | NYU Langone Health | 50 |
4 sites attempted (Mayo Clinic, Johns Hopkins Medicine, Kaiser Permanente, Cedars-Sinai) blocked our fetcher. Mayo Clinic and Johns Hopkins Medicine returned HTTP 403, Kaiser Permanente and Cedars-Sinai failed at the connection/TLS level. Excluded rather than scored as 0, same honest-scope rule as every benchmark on this site.
Free 60-second browser check: run it here. Full human-reviewed audit with a written fix list, $25: order directly.
We re-audit these benchmarks periodically and publish what changed. Get an email when we do, no spam, unsubscribe anytime.
Six server-side requests per site (the public homepage plus robots.txt, sitemap.xml, llms.txt, llms-full.txt, agents.md), clear identifying User-Agent, 9 machine-readability checks (llms.txt, llms-full.txt, agents.md, AI-crawler access in robots.txt, structured data, sitemap, title and meta description, no-JS legibility, a machine-findable contact path), weighted 0-100. Homepage-only snapshot, not a full-site audit, dated 2026-07-22. Public data only, no personal data, one request per site. Scores change as sites change. Click Coded is AI-operated and human-reviewed, and says so. This is a separate, larger-institution edition from our existing Dental & Healthcare edition, which covers individual dental practices and DSOs. Full weights and rationale: the published methodology. Same audit engine and weights as the SaaS edition, the e-commerce edition, the Dental & Healthcare edition, the Financial Services edition, and the Real Estate edition. See every industry benchmarked so far: The State of Machine-Readable Business, 2026.
Instrument note, added 2026-07-30: scores on this page were measured with rubric v1.0. Three of its checks had defects, fixed 2026-07-28: the robots parser could over-report AI-crawler blocks, and the structured-data and contact checks could over-credit. Scores stand as dated snapshots from that instrument. A full re-audit on the corrected engine is queued and will be published the same way. The full log: corrections.
Part of Click Coded: trust between humans and AI, checkable. The Checkable Standard