{
  "$type": "site.standard.document",
  "bskyPostRef": {
    "cid": "bafyreibzivtizxxh3cle5fdlwqhgnamhiu3ehfehuweiyfgyuly7ov2m2a",
    "uri": "at://did:plc:klkgxrhct7epqznuvf6tawoy/app.bsky.feed.post/3mlc5oulwsk52"
  },
  "coverImage": {
    "$type": "blob",
    "ref": {
      "$link": "bafkreigslirolzjn47wyhrj7tfaiu53mnpb53mijsruj5ibr4pcspym3a4"
    },
    "mimeType": "image/jpeg",
    "size": 81548
  },
  "path": "/commentary/2026/05/protecting-federal-ai-systems-a-primer-on-rag-and-securing-ai-driven-data-workflows/",
  "publishedAt": "2026-05-07T20:24:28.000Z",
  "site": "https://federalnewsnetwork.com",
  "tags": [
    "Artificial Intelligence",
    "Big Data",
    "Commentary",
    "Cybersecurity",
    "IT Modernization",
    "Technology",
    "Controlled unclassified information",
    "Federal Information Security Modernization Act",
    "FedRAMP",
    "Gina Scinta",
    "large language models",
    "National Institute of Standards and Technology",
    "Personally Identifiable Information",
    "post quantum cryptography",
    "software as a service",
    "Thales"
  ],
  "textContent": "RAG is a model that connects large language models to live agency knowledge bases — enabling grounded, mission-specific responses, rather than generic outputs.",
  "title": "Protecting federal AI systems: A primer on RAG and securing AI-driven data workflows"
}