agentic checks passed 45% readiness - how well this site can be read, trusted and transacted with by AI agents
Last checked
upenn.edu is live and passes 10 of 30 agentic-readiness checks (45%). It runs on drupal on nginx over HTTPS.
For AI agents, upenn.edu's strongest signals are clean semantic HTML, tidy, crawlable markup, fully indexable pages, and a visually stable layout. Average entity density 41.9% across 1 pages (target >15%).
Its main gaps are text that is hard for agents to extract, no structured tables or lists, few clear definitions, and no self-contained answer passages. The weakest area is Structured data; addressing it first would raise this score the most.
Agent interaction
✓Semantic HTML5 & AccessibilityARIA attributes found for accessibility
✓Clean, Crawlable HTMLPage has title and meta description
✗Extraction Friction ScoreAverage sentence length: 52.7 words - too long for AI snippets
✓Indexability & Snippet EligibilityPages are indexable and snippet-eligible - the precondition for Google AI features is met
✓Layout Stability & Responsiveness66/74 images lack explicit width/height - the most common cause of layout shift (CLS)
✓Canonical URL StrategySingle canonical tag present (no duplicates)
✗Speakable SchemaNo JSON-LD found across homepage - cannot assess speakable schema
AI discovery
✗llms.txt FileNo llms.txt file found at https://upenn.edu/llms.txt (connection failed)
✗robots.txt for AI CrawlersNo explicit AI crawler rules in robots.txt
✓Sitemap Completeness78 URLs have lastmod dates
✗RSS/Atom FeedHomepage does not link to an RSS/Atom feed in <head>
✗Internationalization SignalsNo hreflang alternate links found
✗Content Licensing & AI PermissionsNo ai.txt file found
Trust & transparency
✓Entity Authority & E-E-A-TSocial media / sameAs references found on homepage
✗Creator TransparencyCreator visibility is weak on content-like pages
~Methodology TransparencySome process transparency exists, but it is inconsistent
~AI Assistance DisclosureNo AI-assistance disclosure found on sampled pages (neutral - the engine cannot tell whether AI was used)
✗Visible Date SignalNo visible date signals found across homepage (no <time> elements, no JSON-LD dates, no article meta dates)
✓Title & Meta Quality1/1 pages lack a usable meta description
~Content Freshness SignalsNo JSON-LD date properties (datePublished/dateModified) found across homepage
✗Author & Expert SchemaNo Person schema found across homepage
Every check is a verifiable fact about upenn.edu's live pages. Scoring follows Google Lighthouse agentic-browsing: a fraction of concrete checks, not an invented 0-100.
How to improve for AI agents
The highest-impact changes to make upenn.edu more agent-ready, in priority order.
1 Add structured tables and lists critical impactmedium effort
Present upenn.edu's comparison and spec data as real HTML tables and lists agents can extract.