Foundations
Type: index · Status: current
Core theory that the rest of the KB builds on. These notes define the quality criteria, the design methodology, and the fundamental constraints that shape every other decision.
Notes
- a good agentic KB maximizes contextual competence through discoverable, composable, trustworthy knowledge — unifying theory: three properties serve contextual competence under bounded context; five operations improve them; Deutsch's reach criterion measures knowledge quality
- context-efficiency-is-the-central-design-concern-in-agent-systems — context is the scarce resource; nearly every architectural pattern is a response to volume or complexity pressure
- programming-patterns-get-a-fast-pass-but-other-borrowed-ideas-must-earn-first-principles-support — borrow from any source, filter through first principles; programming patterns get a fast pass
- short-composable-notes-maximize-combinatorial-discovery — the library exists for co-loading; short atomic notes maximize the surface area for cross-cutting discovery
- a-knowledge-base-should-support-fluid-resolution-switching — KB quality measured by how fluidly it supports moving between abstraction levels
- mechanistic constraints make Popperian KB recommendations actionable — bridges conjecture-and-refutation with bounded-context mechanics
-
Alexander's patterns connect to knowledge system design at multiple levels — (speculative) pattern language as document types, generative processes as codification
-
agent context is constrained by soft degradation not hard token limits — the binding constraint is the soft degradation curve, not the hard token limit; agents are in the same soft-bound family as human cognition and organizational learning
- soft-bound traditions as sources for context engineering strategies — catalog of twelve traditions with transfer assessment: what's already working, what's plausible, what's aspirational
Other tagged notes
- Effective context is task-relative and complexity-relative not a fixed model constant — Synthesizes Paulsen MECW, ConvexBench, and GSM-DC — usable context varies with task type, compositional complexity, and irrelevant context load, so nominal window size is a misleading abstraction