Always-on auditing of your llms.txt file against every best practice on llmstxt.org. The Sentry catches missing files and incomplete information before AI channel crawlers do. Cortex handles the fix.
Continuous audits of your llms.txt against the 12 defined best practices on llmstxt.org. Sentry catches what fails. Cortex fixes it.
HTTPS GET returns 200 with a non-empty body.
Origin redirects http://llms.txt to https://. No insecure cleartext.
Response Content-Type is text/plain or text/markdown.
First non-blank line is # SiteName at the top of the file.
File contains at least one ## section that includes one or more markdown links.
Every link uses markdown syntax. No bare URLs, no HTML anchor tags.
The body contains zero <tag> markup. llms.txt is pure markdown.
HEAD request to every linked URL succeeds. No 4xx, no 5xx, no timeouts.
A > summary block right under the H1, in plain English, ≤ 280 chars.
Each section's bulleted links include a one-line description of what the URL contains.
A final ## Optional section listing deprecated or secondary URLs.
An expanded /llms-full.txt file is also available at the site root.
Paste your homepage URL. Sentry fetches your llms.txt, runs all 12 rules, and returns a full audit with a letter grade and per-rule prescriptions. No signup, instant results, always free.
Sentry fetches your file, runs the 12 rules, and renders the full result page before your next sip of coffee.
Each failed rule ships with a prescription paragraph. Hand it to engineering and the file is fixed before lunch.
Add your site to the daily Sentry sweep with one click. New regressions get caught the next morning.
One brain. Thirty-six pairs of eyes. Sentries monitor every visibility signal that decides whether search engines, AI engines, and ad platforms show you. Cortex reads what they see, weighs it against a unified corpus of platform documentation, and acts. Every move follows a defined decision protocol: action stated, reason given, impact named.