For you
Architects
Own where judgment lives, how units compose, and what the system means.
Cover for Architects13 concepts curated for architects.
Back to home
Illustration for The Thoughtware architectVocabulary above the code
9 minThe Thoughtware architect
Someone must own decision maps, cognitive unit boundaries, library strategy, evaluation policy, and human authority placement, not model selection alone.
Illustration for The Thoughtware Map and GrammarShared workshop notation
10 minThe Thoughtware Map and Grammar
Shared map and specification language for outcomes, behaviour, memory, authority, and evaluation, so construction does not restart from features every sprint.
Illustration for Making the specification executableSpecs that compile to checks
10 minMaking the specification executable
A Thoughtware Map and specification hold framing. Making them executable means deriving runnable architecture with traceability, not slide decks that never become contracts, suites, and gates.
Illustration for Where does a decision live?One home for each judgment
7 minWhere does a decision live?
Every open decision should have one primary home in the architecture, not smeared across prompts, UI, and middleware. This page explains why locality errors make systems untraceable and unmaintainable.
Illustration for Judgment chainsLinked judgments need owners
10 minJudgment chains
Outcomes are produced by sequences of interpretations, checks, comparisons, and actions, not by one feature or one prompt. Mapping the chain makes hidden cognitive burden visible and gives every failure an address.
Illustration for Thoughtware SystemOne governed whole
10 minThoughtware System
A Thoughtware system composes agents, skills, cognitive units, libraries, memory, deterministic code, evaluation, and human authority into one governed architecture toward defined outcomes.
Illustration for Where the cognitive unit ends and the agent beginsJudgment, procedure, or pursuit
8 minWhere the cognitive unit ends and the agent begins
A cognitive unit owns one judgment. A Skill owns a known procedure. An agent owns a goal whose path may still need discovery.
Illustration for Lessons from software architectureBorrow structure, not organs
12 minLessons from software architecture
Bounded contexts, encapsulation, and separation of concerns solved composition for deterministic systems. Thoughtware extends those lessons to judgment, with one critical divergence around evaluation.
Illustration for Abstraction does not remove responsibilityHiding does not transfer blame
10 minAbstraction does not remove responsibility
Generators, libraries, and agent loops make cognition easier to compose. They do not transfer ownership of outcomes, authority, or evaluation to the model or the tool that invokes it.
Illustration for What a name buysShared vocabulary pays rent
10 minWhat a name buys
Engineers resist naming meetings until they see what a precise name for a judgment actually buys, boundaries, tests, libraries, and someone to blame when the answer is wrong.
Illustration for Skill versus capabilitySemantics versus packaging
9 minSkill versus capability
Skill is a defined responsibility boundary. Capability is informal unless mapped to skill, cognitive unit, or library package.
Illustration for Acting is not agencyPerforming is not pursuing
9 minActing is not agency
A Skill may write to the world. Reach does not create an agent. Agency begins when evidence can change what work should be undertaken next.
Illustration for Skill library versus cognitive unit libraryTwo inventories, two cuts
10 minSkill library versus cognitive unit library
Cognitive unit libraries publish bounded judgments. skill libraries publish responsibility-sized procedures, different versioning, evaluation, and substitution semantics.