Work

Experimental workshop space. Purpose-driven working artifacts that haven't codified into notes yet.

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

• 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
• type-system-rationalization — reconciling frontmatter types, directory-scoped types/ templates, and path-based exemptions into one coherent design
• 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
• agent-memory-design — designing an ideal agent memory system: store everything (especially session logs), invest all design intelligence in retrieval/activation
• philosophy-borrowing — evaluating Peirce's abduction, Quine's web of belief, speech-act theory, and Carnap's explication as operational borrowings for KB methodology
• system-documentation — how to document the current commonplace system: separating general theory from system-specific design, finding an entry point beyond CLAUDE.md and scattered ADRs