Problem
Documents often reference other standards, frameworks, and related docs in bibliographies, "further reading" sections, and inline hyperlinks. We currently don't capture these, missing an opportunity for automated document discovery.
Proposal
Extract bibliography entries, citations, and hyperlinked documents as external_reference facts to enable a "retrieve next level" workflow: upload one document, discover 6 more to fetch.
Implementation
- Add
external_reference fact type to identify citations, bibliography entries, and hyperlinks to external documents
- Update extraction prompt to classify external document references
- Build workflow to present extracted references as retrievable documents
- Add UI for "fetch referenced documents" action
- Consider pattern matching for common citation formats (ISO standards, NIST, RFCs, etc.) and URL patterns
Expected Outcome
User uploads SOC 2 report that references ISO 27001, NIST CSF, links to 4 policy documents → system presents list of 6 documents to retrieve → user clicks "fetch all" → knowledge base grows automatically.
Problem
Documents often reference other standards, frameworks, and related docs in bibliographies, "further reading" sections, and inline hyperlinks. We currently don't capture these, missing an opportunity for automated document discovery.
Proposal
Extract bibliography entries, citations, and hyperlinked documents as
external_referencefacts to enable a "retrieve next level" workflow: upload one document, discover 6 more to fetch.Implementation
external_referencefact type to identify citations, bibliography entries, and hyperlinks to external documentsExpected Outcome
User uploads SOC 2 report that references ISO 27001, NIST CSF, links to 4 policy documents → system presents list of 6 documents to retrieve → user clicks "fetch all" → knowledge base grows automatically.