Tags
Type: kb/types/tag-readme.md · Status: current
Browse the KB by tag. Each tag page has a curated editorial section and an auto-generated listing of all notes with that tag.
For current-state documentation about the live Commonplace system rather than transferable theory, start at ../reference/README.md.
Tag Indexes
- Foundations — core theory: contextual competence, bounded context, reach, design methodology, composability
- Architecture — how Commonplace is structured and installed: repo layout, control-plane design, file-based storage
- Evaluation — what works, what doesn't, what needs testing
- Learning theory — how systems learn, verify, and improve; covered by seven child tags (enforced), so its README routes rather than enumerates:
- Deploy-time learning — the framework: adaptation through durable inspectable artifacts
- Constraining — narrowing interpretation space, codification, relaxing
- Distillation — targeted extraction of use-shaped artifacts
- Discovery — positing generals, recognizing instances; reach
- Artifact analysis — the four-field vocabulary for retained artifacts
- Agent memory — memory architecture and policy (also a top-level area)
- Document system — document types, writing conventions, and validation rules for structured notes
- Computational model — programming-language framing for LLM instructions and orchestration
- Tool loop — loop exposure, hidden schedulers, and framework-owned tool-loop failure modes
- Context engineering — getting the right knowledge into bounded context at the right time
- Failure modes — characteristic ways knowledge can exist without changing agent behavior
- Links — link semantics, navigation behavior, and link-management methodology
- Type system — why documents have types, what roles they serve, how structured writing improves quality
- LLM interpretation errors — error taxonomy, oracle theory, error correction, and architectural responses to imperfect LLM interpretation
- Observability — making hidden state, hidden failure, and quality drift visible enough for operators and maintenance loops to act on
- KB maintenance — operations, audits, and maintenance methodology
- Related systems — external systems tracked for comparison and convergence signals
Workshop Layer
- a-functioning-kb-needs-a-workshop-layer-not-just-a-library — the library type system models durable knowledge but not work-in-motion
- evolving-understanding-needs-re-distillation-not-composition — when a consumer needs the whole evolving picture, re-distill into a single narrative rather than composing notes
Gaps
- automating-kb-learning-is-an-open-problem — the open problem is automating judgment-heavy mutations (connections, groupings, synthesis)
- claw-learning-loops-must-improve-action-capacity-not-just-retrieval — learning must improve action capacity, not just retrieval
- brainstorming-how-to-enrich-web-search — enriching web search by temporarily expanding the corpus and applying connection methodology