← Content library

Checklist / RAG and knowledge systems / Intermediate

RAG Content Readiness Checklist

A pre-ingest review of whether a content set is worth indexing yet. Directional, not a formal audit.

For Platform and documentation teams

01Discovery

  • A sitemap or equivalent URL list exists and resolves
  • Crawl scope is defined by path rules, not by guesswork
  • Versioned or localised duplicates are identified
  • Canonical tags are present and respected by the crawl

02Content

  • Pages carry a single clear H1 and a sane heading hierarchy
  • Code blocks and tables survive normalization intact
  • Navigation, footers, and banners are removed from retained text
  • Pages that are pure navigation are excluded from the index

03Metadata

  • Each document records title, canonical URL, and section path
  • Product or version is captured where the content is version-specific
  • A last-retrieved timestamp is stored with every document

04Maintenance

  • A recrawl cadence is agreed and owned by someone
  • Removed pages are deleted from the index, not left orphaned
  • A small retrieval test set exists and is run after each recrawl
ragdocumentationcrawling