How a Research Tank Improved Its AI Visibility for Policy Reports

Three architectural problems explained why the research was invisible to AI synthesis.

1. 1

   Locked narrative architecture (PDF-only insight)

   The core value of the organization—its data tables, policy recommendations, and methodology—was nested entirely inside multi-page PDF documents. The corresponding HTML landing pages contained only brief, stylized marketing copy and a download button. While modern LLMs can parse PDFs, doing so requires significantly higher computational cost during indexing; LLMs prioritize high-quality, structured HTML text on the primary page canvas. By hiding the substance in a download link, the organization was effectively filtering itself out of the AI training and retrieval pipelines.

2. 2

   Disconnected scholar entities

   Scholar bio pages were treated as simple corporate "About Me" pages. They listed names and narrative text but lacked structural connections to the reports those scholars authored or the specific policy domains they specialized in. If an AI model cannot programmatically verify that a report on economic policy was written by a credentialed economist with a verifiable publication history, it down-ranks the content's reliability and avoids citing it as an authoritative source.

3. 3

   Vague, indirect copywriting

   Page introductions relied on academic jargon or generalized, narrative throat-clearing (e.g., "In an era of unprecedented change, addressing the complex challenges of our communities requires a multifaceted approach to policy valuation..."). When a model scans a page for a direct answer to a prompt, vague prose dilutes the primary entities. The model abandons the text in favor of sources that use clear, direct, and explicit subject-verb-object structures.

The fixes that turn flat, unstructured documents into machine-readable semantic content.

The backend markup that connects a researcher entity to their credentials, employer, and policy domains.

{
  "@context": "https://schema.org",
  "@type": "ProfilePage",
  "mainEntity": {
    "@type": "Person",
    "name": "Dr. Aris Vance",
    "jobTitle": "Senior Research Fellow",
    "worksFor": {
      "@type": "ResearchOrganization",
      "name": "The Public Policy Institute"
    },
    "alumniOf": {
      "@type": "CollegeOrUniversity",
      "name": "University of Michigan"
    },
    "knowsAbout": [
      "Energy Infrastructure",
      "Grid Modernization",
      "Public Policy"
    ]
  }
}

What people ask most about making research citable by AI.

Related guides to take you deeper.