Work
Experimental workshop space. Purpose-driven working artifacts that haven't codified into notes yet.
Navigation: directory index.
Each workshop is a directory exploring a specific workflow end-to-end: from question through sourcing and extraction to finished notes. The goal is to discover what patterns actually emerge from use, rather than designing structure upfront.
Active Workshops
- agent-memory-design — continuation workshop for discussing revisions and companion artifacts around
kb/notes/designing-agent-memory-systems.md - vocabulary-redesign — redesigning the always-loaded and library-level vocabulary so terms stay discriminating, teachable, and operationally useful
- aris-full-trial — running a private full-ARIS paper-production trial while keeping only framing and lessons learned in the public KB
- research-wiki-integration — evaluating whether ARIS Research Wiki should become a commonplace workshop subsystem, source workflow upgrade, or only a set of borrowed lifecycle patterns
- gate-refactor — moving review storage and selector state from monolithic review bundles to gate-native definitions, memberships, and per-gate acceptances
- validation — making validation a reliable part of the workflow: when, what, and how to validate (hooks, skill upgrades, periodic revalidation)
- tool-loop-control — rewriting the framework-loop note so it starts from why the standard tool loop exists and where convenience should end
- obsidian-affordances — deciding which Obsidian-facing affordances are useful compatibility layers versus representation drift for a repo-native KB
- harness-taxonomy-convergence — mapping five independent harness decompositions into one table; uncovered a structure × governance two-axis split
- philosophy-borrowing — evaluating Peirce's abduction, Quine's web of belief, speech-act theory, and Carnap's explication as operational borrowings for KB methodology
- agent-complexity-theory — formal consequences of the bounded-context orchestration model; candidate theorem sketches for academic collaboration
- write-type-resolver — migrating
type:from an enum-string to a path-valued pointer addressing a hand-authored instructions doc per type - semantic-search-replacement — evaluating whether to replace qmd as the semantic-search layer, and with what
- latent-space-generation-without-training — exploring whether embedding-guided novelty-generation papers can become a practical no-large-training workflow
- review-revise-gated — finding review/revise arrangements that reliably produce the manual-edit quality bar, then codifying as reusable instructions
- auditable-llm-editing — testing whether sparse, anchored writing state prevents accidental claim drift across repeated LLM editing passes
- shipping-model — deciding how commonplace ships its content so user collections stay theirs while our library sits alongside as a read-only dependency
- lifecycle-management — mapping the full artifact life-cycle (intake, promotion, maturation, retirement); the
agent-memory-designtest case landed as anote + synthesistrait inkb/notes/designing-agent-memory-systems.md