If your dashboards can’t answer “what if”, they’re already obsolete.
The architectural argument for moving from descriptive analytics to causal reasoning — without throwing your data warehouse away. 6 min read
1 min read
The architectural argument for moving from descriptive analytics to causal reasoning — without throwing your data warehouse away. 6 min read
Standard retrieval-augmented generation indexes documents by topic. For enterprise architecture work, the relevant retrieval object is not the document but the decision trace: a typed walk across the context, causal, and knowledge layers. Indexing the trace category rather than associated documents produces a retrieval primitive that respects compositional structure. This article specifies four retrieval patterns over the trace category, sketches a property-graph implementation and argues that selective embedding — over node content, not trace structure — is the right hybridisation point.
Business decisions are rarely the conclusion of a single inference: they assemble facts, mechanisms, and scope judgements drawn from heterogeneous graph layers. This article argues the right primitive for capturing such assemblies is a decision trace — a typed graph walk traversing the context, causal, and knowledge layers of the enterprise architecture, recording the local material the decision rests on. The trace is a provenance object in the W3C PROV sense, typed by the layer it traverses — and that typing is what makes it operationally useful.