This vision paper proposes “Knowledge Engines” as a framework for understanding how intelligent systems—both human and artificial—systematically discover, integrate, and generate knowledge. We argue that history’s greatest minds functioned as knowledge engines, processing information through cycles of ingestion, analysis, synthesis, and communication, guided by curiosity, fearlessness, and willingness to challenge established beliefs. We propose a taxonomy of nine integrated capabilities—ingestion, digestion, analysis, calculation, comparison, connection, association, analogy, and multi-modal communication—synthesizing decades of prior work in expert systems, knowledge representation, and cognitive architectures for the LLM era. Our framework emphasizes that ambitious goals like “finding a cure for cancer” require comprehensive integrated systems, not merely powerful models, combining AI capabilities with structured processes, specialized tools, and systematic approaches. We present CopernicusAI as a working implementation of the Knowledge Engine framework, demonstrating feasibility through a fully deployed system with 12,000+ indexed research papers, operational knowledge graph visualization, vector search, and RAG capabilities. While extensive validation remains necessary, the system demonstrates that the framework can be instantiated in practice. This vision paper aims to establish “Knowledge Engine” as a generic term describing systems that systematically transform information into knowledge, providing both a theoretical blueprint and a concrete implementation for future research.
Gary Welz (Tue,) studied this question.