Technology
Ontology — how kernalic builds structure into data.
What we mean by structure
The structure kernalic builds is an explicit definition of how data relates. Which document supersedes which, which concept contains which — only once those relationships are defined can data be traced, and its history stops being something anyone has to compile.
Ontology, the tool we build it with
We implement that structure as an ontology: a machine-readable definition of the concepts and relationships inside a domain. General-purpose AI models do not know a domain's exact relationships, so we state them explicitly in an ontology and combine that with the model's judgment to produce results that are both more accurate and explainable.
One principle, applied differently per brand
Relationships between patent documents (IPSnap), correspondence between standard versions and patent claims (SEPPi) — the subject differs, but the principle is the same: define the relationships as structure, and make them traceable.