What counts as a primary source
DABAR accepts structured and unstructured inputs across a wide range of formats:Documents
PDFs, Word documents, plain text, spreadsheets.
Media
Audio recordings, video, images, maps.
Live data
SQL databases, internal APIs, approved external APIs.
Web
Specific URLs you whitelist — never unverified open-web content.
The “AI citing AI” problem
Most AI research tools pull from the open internet. That means:- They may cite pages that were themselves written by AI.
- They cannot distinguish authoritative from unauthoritative sources.
- Their outputs cannot be audited — the ground truth changes daily.
Where sources live
Sources in DABAR exist at two levels:Policy-level sources
Defined on a Politic viaknowledgeFiles. These are the authoritative references the policy reasons against — regulations, playbooks, internal guidelines.
Project-level sources
Defined on a Project viafiles. These are the specific inputs DABAR is being asked to analyze — a loan application, a contract, a due diligence packet.
document, url, photo, video, audio, text.
How DABAR uses them
When a project runs, DABAR:- Ingests every source, preserving structure (page numbers, timestamps, cell references).
- Grounds its reasoning against the policy’s
knowledgeFiles. - Cites the exact source and location for every claim it makes.
- Flags anything that cannot be grounded — never fabricates a citation.
Source control = audit trail
Because every output is traced to a source you approved, DABAR produces a complete audit trail by default. That makes outputs:- Defensible in legal and compliance contexts.
- Reproducible — re-run the same project and the citations still point where they pointed.
- Portable — the evidence travels with the answer, not hidden in a model’s weights.
Next
Policy Engine
How DABAR decides what a source means.
Autonomous Agents
Turn a sourced knowledge base into an agent that takes action.