STRUCTURED INPUTS
CSV, Parquet, DuckDB and NDJSON are the current priority formats.
+Engine / DataAuthority
DATAAUTHORITY ENGINE: QUERY DATA. KEEP THE EVIDENCE.
The DataAuthority Engine is being finalized. Its current priority is structured data: controlled inputs, traceable transformations and outputs that retain source, coverage, contradictions and limits.
In developmentWhat is Data Authority? →
01 / What the engine is for
FROM STRUCTURED DATA TO TRACEABLE FACT UNITS.
The engine starts where inputs, transformations and outputs can be controlled precisely. In our architecture, an atom is a unit of fact tied to a source, version, context and the conditions that constrain its use. This is our internal modeling term, not an industry standard.
ATOMS
The engine is designed to decompose results into traceable fact units instead of one opaque global verdict.
PROVENANCE + QA
Source, version, transformations and checks remain connected to the data path.
LIMITS
Unknown, conflict, insufficient coverage and unsafe inference remain explicit.
02 / From file to result
STRUCTURE, ATOMIZE, CHECK, THEN CONCLUDE.
A missing observation is not automatically a measured zero. An absent source is not proof of absence. A conflict between two sources is not resolved merely because one value is easier to use.
CSV / ParquetDuckDBNDJSON
↓Atoms + provenance + QA↓Result + evidence + limits03 / Test on request
GIVE US A DATASET. WE WILL SHOW YOU WHAT THE ENGINE CAN ACTUALLY SUPPORT.
The engine is not yet open as a self-service product. We can select exploratory cases on request: a structured sample, a concrete question, and a walkthrough of what the data supports — and what it does not support.
Current boundary: PDFs and documents are considered case by case when they contain native, verifiable text. Arbitrary scanned-document OCR is not presented as a guaranteed capability.