Sources & coverage
Where can the answer come from?
Source selection decides where an agent looks: the public web, a specialist collection, or an internal corpus. Coverage includes which records are searchable, how much content is accessible, and how recently it was updated. Finding a document in an index does not necessarily mean receiving its full text.
The webPages · news · docs
Specialist sourcesPapers · filings · records
Your dataFiles · messages · tables
Retrieve from the right collection
Start with current web sources. Check publication dates and follow links to the original announcement.
What to understand
- Match the source to the question: public pages, research papers, financial records, and internal policies have different coverage and access requirements.
- Distinguish discovery from access. A title, abstract, or search snippet may help locate a source without supplying the evidence you need.
- Check timestamps and provenance. A page's publication date, its last update, and the time it was retrieved describe different things.
Go to the source
Primary documentation for the ideas in this explainer.
Follow the next part of the system.
Parsing & extraction