Tags Directory

Type: types/generated-index.md

← Parent

  • Agent memory (tag-readme) - Curated head for the agent-memory tag — how agents retain, recall, and govern knowledge across sessions: memory-system requirements, activation, trace extraction, lifecycle, and comparisons of external memory systems
  • Architecture (tag-readme) - How Commonplace is structured and installed — repo layout, two-tree split, control-plane design, file-based storage
  • artifact-analysis (tag-readme) - Curated head for the artifact-analysis tag — the four-field vocabulary (substrate, form, lineage, authority) for classifying retained behavior-shaping artifacts, plus its applications
  • claims-and-grounding (tag-readme) - Curated head for the claims-and-grounding tag — claim titles, claim modality, ground truth and supersession, source grounding and quotes, and grounding evidence from review runs
  • Computational model (tag-readme) - Tag README — PL concepts (scoping, homoiconicity, partial evaluation, typing) applied to LLM instructions, plus the scheduling architecture that follows from context scarcity
  • constraining (tag-readme) - Curated head for the constraining tag — narrowing the interpretation space of artifacts, from conventions to deterministic code; codification, relaxing, and the decision heuristics
  • Context engineering (tag-readme) - Curated head for the context-engineering tag — getting the right knowledge into a bounded LLM context at the right time: routing, loading, scoping, context budgets, scheduling, and what to retain for later loading
  • continual-learning (tag-readme) - Curated head for the continual-learning tag — how a deployed AI system keeps learning outside model weights through retained prompts, rules, tools, and tests, and why that fits the Bitter Lesson
  • curation (tag-readme) - Curated head for the curation tag — keeping indexes, tag heads, and the note set usable as the KB grows: index recall, quality scores, staleness signals, retirement, and hygiene operations
  • deploy-time-learning (tag-readme) - Curated head for the deploy-time-learning tag — the phenomenon that deployment meets users, surprises, and forces change after first release; what use reveals that design could not
  • discovery (tag-readme) - Curated head for the discovery tag — positing a general concept and recognizing particulars as its instances; explanatory-reach as the value of what discovery produces
  • Document system (tag-readme) - Curated head for the document-system tag — how KB documents are typed, written, structured, tested, and retained: type contracts, writing conventions, text testing and validation, documentation retention, and claim repair
  • Evaluation (tag-readme) - Curated head for the evaluation tag — how claims, changes, and agent outputs are judged and tested: oracles and LLM judges, warrant versus theory fit, experiment and benchmark design, and evidence records from Commonplace review runs
  • Failure modes (tag-readme) - Curated head for the failure-modes tag — recurring ways knowledge and claims in an agent-operated KB fail to do their job: stored but never activated, promoted without authority, over-generalized, or escaping review by widening or narrowing
  • improvement-loop (tag-readme) - Curated head for the improvement-loop tag — proposal-selection loops: search for candidates, reject-capable evaluation, operative retention, search control, backtracking, and oracle quality
  • KB maintenance (tag-readme) - Curated head for the kb-maintenance tag — keeping an agent-operated knowledge base healthy as it grows: three child areas (review-system, claims-and-grounding, curation) plus the dynamics, evidence, and open proposals that cut across them
  • Learning theory (tag-readme) - Curated head for the learning-theory tag — how systems learn, verify, and improve: accumulation, continual learning, verification, memory, and self-improvement, anchored on the theory builder, with routes through its child areas
  • Links (tag-readme) - Curated head for the links tag — linking theory, link labels and relationship semantics, link position and strength, backlinks, link-following versus search navigation, and lineage links
  • LLM reliability (tag-readme) - Why LLM output deviates from intent — underspecification, interpreter failure, indeterminism — and the machinery for detecting and correcting it, from oracle theory and error correction to architectural separation
  • Methodology (tag-readme) - Curated head for the methodology tag — how an agent selects, borrows, and is controlled by a methodology: selection among incompatible approaches, borrowing through artifacts or weights, intent as control, and method transfer
  • Observability (tag-readme) - Index of notes about making hidden state, hidden failure, and quality drift visible — runtime inspectability, degraded-execution signals, and maintenance-oriented detection mechanisms
  • reflection (tag-readme) - Curated head for the reflection tag — reflective systems and self-representation: how a system reads and revises its own rules, what addressable retention buys, and where reflective coverage stops
  • review-system (tag-readme) - Curated head for the review-system tag — LLM review of notes: gates and criteria, assays, verdict freshness and invalidation, review cost, and proposals for the review pipeline
  • Self-improving systems (tag-readme) - Curated head for the self-improving-systems tag — systems that make operative, evidence-responsive changes to their own organization; definition, objective, accumulation, and six child areas from theory builder to continual learning
  • software-factory (tag-readme) - Curated head for the software-factory tag — software factories, software houses, and factory development: family-specific production machinery, how agents build it, and what factory learning means
  • Tag heads for kb/tags/
  • theory-builder (tag-readme) - Curated head for the theory-builder tag — systems that apply conjecture and refutation to stated theories: addressable and tentative theory, criticism, theory fit, program theory, reach-assessment
  • Trace-learning (tag-readme) - Curated head for the trace-learning tag — external systems that learn from agent traces: raw traces accumulate, then a distillation step produces rules, memories, prompts, or weights; the tag marks system reviews whose analysis found that loop
  • Type system (tag-readme) - Index of notes about the document type system — why types exist, what roles they serve, how they improve output quality, and how they're structured
  • warranted-autonomy (tag-readme) - Curated head for the warranted-autonomy tag — which decisions an AI agent is warranted to take over from humans, how oracles bound that, and how autonomy is measured