Knowledge RAG

Design Knowledge Base

Community-maintained principles reviewed before publication and retrieved as Agent design constraints.

2 published principles / 192 in library

Data Visualizationdata-transform / provenance

Visualization Transform Provenance

Charts must record filter, aggregate, bin, timeUnit, join, missing-value, and sorting logic; otherwise users cannot audit why the chart looks the way it does.

Data-visualization trust comes not only from graphics but also from an explainable transform chain. Every aggregation, filter, and derived field should be traceable.

95%Resource Licensinggenerated-assets / provenance

Generated Asset Provenance Record

AI-generated assets have provenance too: tool, model, prompt, source references, edit history, rights risks, and reuse boundaries must be recorded together.

An asset library cannot treat AI generated as a license or source explanation. Reuse depends on input rights, depicted subject, edit chain, verification signals, and usage context.

94%