{
  "schemaVersion": "crawler-atlas-1",
  "atlasVersion": "atlas-2026-07-28-v1",
  "canonical": "/atlas/seed-urls",
  "title": "Seed URLs",
  "category": {
    "slug": "discovery",
    "title": "Discovery and crawl frontiers"
  },
  "definition": "Seed URLs are the starting addresses placed into a crawler before link extraction begins.",
  "mechanism": "A seed can come from a prior crawl, a sitemap, a manual submission, a feed, or a link found on another host. Its quality determines which connected region of the web becomes reachable.",
  "validation": "Record the entrypoint separately from later discoveries, then compare which pages become reachable from each seed set under the same page and depth budget.",
  "commonFailure": "Treating every visited URL as a seed hides the actual discovery path and makes coverage comparisons impossible.",
  "related": [
    "/atlas/crawl-frontier",
    "/atlas/internal-links"
  ],
  "modified": "2026-07-28"
}