Entities

Every piece of information in HASH is stored as a typed entity within a knowledge graph. People, companies, documents, events, and the links between them form an interconnected web that represents your complete operational context.

HASH stores data along two time axes: ‘valid time’ (when something was true in the real world) and ‘transaction time’ (when it was recorded in the system). This enables powerful temporal reasoning — ask questions like ‘what did we know about X at time Y?’ with precision. Full provenance is maintained across both.

By tracking how entities change over both time axes, HASH supports causal inference at the data layer. Understand not just what changed, but why, and trace the chain of events that led to any given state.

The entity graph doubles as a rich, structured context store for AI agents and language models. Instead of flat document retrieval, agents can traverse typed relationships to find precisely the information they need.