System Capabilities

Architecture
System Architecture

Capabilities are the Currency of Agency

We do not build "Features" (marketing units). We build "Capabilities" (atomic units of system potential). This shift creates a composable Intelligence Space where functionality is addressable, permissioned, and evolutionary.

Core Principles
01

The Ontology of Power

To enable an Intelligence Space that can reason about its own abilities, we must formalize what "ability" means.

AXIOM 01

Discrete & Addressable

Every capability must have a unique, stable Identity (ID). If you cannot reference it by ID, it does not exist in the system.

capability:dialogue.branching
AXIOM 02

Agent-Agnostic

Capabilities exist independently of the Agents that use them. Agents are merely collections of entitled Capabilities.

AXIOM 03

Composable

Capabilities define their dependencies. Complex abilities are built by composing atomic primitives, creating a directed graph of system potential.

AXIOM 04

Evolutionary

A Capability has a lifecycle. It is born as a Concept, matures to Stable, and dies as Deprecated. The system must know where every capability stands in time.

src/lib/capability/types.ts
export interface CapabilityDefinition {
  readonly id: CapabilityId;
  readonly name: string;
  readonly domain: CapabilityDomain;
  readonly status: CapabilityStatus;
  
  // Behavioral Traits
  readonly traits: ReadonlyArray<CapabilityTrait>;
  
  // Architecture
  readonly manifestation: CapabilityManifestation;
}
Type Safe
Immutable
Centralized
02

The Holon Model

We extend the capability model into a recursive systems architecture. Borrowing from Arthur Koestler's Systems Theory, we treat every component as a Holon: a system that is simultaneously a whole (containing subsystems) and a part (of a larger system).

Purpose

Why does this system exist? Its teleological goal.

presentationinteractionbehaviorstoragecommunicationorchestration

Agency

How autonomously does it act?

passivereactiveproactiveautonomous

Observability

How visible is its internal state?

opaqueinspectableobservabletransparent

Mutability

How does it change over time?

immutableconfigurablemutableadaptive

The System Contract

Every component must fulfill a universal contract to participate in the Intelligence Space. This ensures predictable composition and inspection.

interface SystemContract {
  // Identity
  readonly id: SystemId;
  readonly purpose: SystemPurpose;
  
  // Boundary
  readonly interface: SystemInterface;      // Provides
  readonly dependencies: SystemDependencies; // Requires
  
  // Behavior
  readonly agency: SystemAgency;
  readonly affordances: ReadonlyArray<Affordance>;
  
  // Structure
  readonly contains?: ReadonlyArray<SystemContract>;
}
Technical Implementation
03

The Registry Model

The Capability Registry is the single source of truth. It sits between the Code (Implementation) and the Experience (User/Agent).

Identity
Definition
What is it?
Lifecycle
Evolution
Is it ready?
Access
Entitlement
Who can use it?

Active Registry

25 capabilities loaded

Shell Navigation

shell-navigation
stable

Controls sidebar visibility and navigation state. Toggle the sidebar to focus on content or reveal navigation options.

platform
global-shortcut

Command Palette

command-palette
beta

Fuzzy-search through all available commands, navigation targets, and actions. Power-user interface for keyboard-first workflows.

platform
global-shortcut, command-palette
user-input

Modal Management

modal-management
stable

Centralized modal and dialog management. Handles opening, closing, and stacking of modal dialogs.

platform
modal

Session Management

auth-session
stable

Manages user authentication session lifecycle: login, logout, token refresh, and session persistence.

platform
header, command-palette
requires-confirmation

Account Menu

account-menu
stable

Access user profile, account settings, and session controls from the header menu.

platform
header

Toast Notifications

toast-notifications
stable

Non-blocking notifications that appear briefly to confirm actions or report errors. Auto-dismiss with optional actions.

platform
toast
background

Theme Toggle

theme-toggle
planned

Toggle between light and dark themes. Respects system preference by default with manual override.

settings
header, settings, command-palette

Preferences

preferences-management
stable

Manage user preferences including theme, notification settings, and keyboard shortcuts.

settings
sidebar, settings, command-palette

Capability Explorer

intelligence-space-capability-explorer
in-development

Explore all registered capabilities in the Intelligence Space. Browse the full catalog of features, their evolution status, affordances, and how they manifest across the application.

meta
sidebar, command-palette

Dashboard

dashboard
stable

Your home base within the Intelligence Space. See recent activity, quick actions, and get oriented on what to do next.

platform
sidebar

Tools

tools
stable

Access interactive prototypes for capturing and structuring thought. Tools are evolved from experiments into production-ready features.

platform
sidebar

Learn

learn
stable

Understand the theory and methods behind effective thinking and sensemaking. Guides, tutorials, and conceptual foundations.

platform
sidebar

Settings

settings
stable

Manage your account, preferences, and integrations. Configure the Intelligence Space to match your workflow.

settings
sidebar

Dev Playground

dev-playground
stable

Development-only route for testing shell functionality, toast notifications, and UI components before integration.

platform
sidebar

Context Engineering

context-engineering
beta

A type-safe decision engine for selecting and constructing optimal LLM prompts based on task requirements (Zero-Shot, Few-Shot, Chain-of-Thought, ReAct).

platform
background

Dialogue

dialogue
stable

Multi-agent dialogue interface for exploring ideas through conversation. Select one or more intelligence agents to engage with your thoughts.

dialogue
sidebar, canvas, command-palette
collaborative

Tool Use

tool-use
in-development

The ability for the Intelligence Layer to reach outside the conversation context to execute code, search the web, or query the database.

dialogue
input-bar
requires-confirmationlong-running

Concept Reference

concept-ref
planned

Direct linking to specific Domain Primitives (Files, Thoughts, Users) using the @ symbol. Resolves ambiguity by explicitly binding symbols to their definitions.

dialogue
input-bar
user-input

Branching

branching
planned

Spawning a temporary "Side Conversation" to explore a specific tangent without polluting the main context stream. Merge insights back when complete.

dialogue
message-menu, input-bar
user-input

Voice Interface

voice-input
planned

Direct audio stream processing that captures speed-of-thought articulation. Bypasses the "Typing Bottleneck" to allow for rapid dumping of raw mental context.

dialogue
input-bar, global-shortcut
background

Manage Council

manage-council
in-development

Create, edit, and configure Councilors—specialized AI personas that assist in dialogue.

meta
command-palette, sidebar, settings
user-input

Select Councilor

select-councilor
in-development

Switch between different Councilors during a dialogue session.

dialogue
message-menu, command-palette
requires-confirmation

Prompt Mutation

prompt-mutation
planned

Iterate on designed instructions using natural language. Critique the output, and the system analyzes your feedback to mutate the underlying prompt—generating optimized versions for review. Build reusable systemic structures for artifacts like marketing content, code modules, or domain-specific building blocks.

synthesis
input-bar, sidebar
collaborativelong-running

Insight Capture

insight-capture
planned

Promote a single agent response from transient dialogue into a permanent Insight. Captured insights become topics on the Landscape Map—a structured knowledge graph connecting your discoveries across conversations.

capture
message-menu
destructive

Thought Analysis

thought-analysis
planned

Decompose a raw thought or message into structured primitives: Intents, Concepts, Tensions, and Invariants. Then synthesize a falsifiable Design Hypothesis—transforming intuition into actionable, testable propositions.

analysis
message-menu
long-running
04

The Dictionary of Agency

We shift our language from "Static Features" to "Dynamic Capabilities".

Traditional "Feature"

"Feature: The User can save files."

System Capability

"Capability: File System Write Access."

Features describe user benefits. Capabilities describe system permissions.

Traditional "Feature"

"Feature Flag: Enable Beta UI."

System Capability

"Lifecycle: Status = Beta."

Flags are binary toggles. Lifecycles are continuous states of maturity.

Traditional "Feature"

"The Pro Plan includes AI Chat."

System Capability

"Pro Plan grants: capability.dialogue.*"

Plans are bundles of Capability IDs, not lists of marketing terms.

Future Roadmap
05

Future Enablement

Metaprogramming

When capabilities are addressable data, Agents can query their own toolset. An agent can ask: "Do I have the capability to search the web?" and adapt its strategy accordingly.

Dynamic Composition

We can compose custom "Agent Profiles" on the fly by mixing and matching capabilities. Create a "Research Agent" by combining [WebSearch] + [NoteTaking] - [CodeExecution].

Granular Governance

Security is no longer a blanket "User" check. It is a precise check: "Does Actor X hold the Entitlement for Capability Y on Resource Z?"

Automated Guidance

The UI can automatically generate "What's New" modals or "Help" tooltips based on the Concept/Description metadata stored in the Capability Registry.

What's Not Covered (Yet)

The current type system focuses on Definition. The following aspects are explicit non-goals for the initial registry but are part of the broader system vision:

  • Runtime State: The registry does not track active instances or transient state (e.g., "Is the voice input currently listening?"). That belongs in the runtime store.
  • Policy Enforcement: The registry defines what exists, not who can use it. Entitlement logic (RBAC, Plans) is a separate domain that consumes the registry.
  • Implementation Mapping: The registry is an interface contract. It doesn't strictly enforce code location (though it hints at `primaryDomain`).
Reference
07

Knowledge Inventory

01

Capability

An atomic unit of system potential. A discrete power that can be granted, revoked, or composed.

Replacing amorphous "features" with addressable data allows the system to reason about itself.

02

Holon

Something that is simultaneously a whole and a part. A basic unit of organization in biological and social systems.

Our "Systems" are holons: complete in themselves, yet parts of larger systems.

03

Purpose

The functional goal or teleology of a system (e.g., Presentation, Storage, Behavior).

Allows architectural validation: "A Presentation system should not mutate Storage."

04

Agency

The level of autonomy a system possesses (Passive → Reactive → Proactive → Autonomous).

Critical for distinguishing between dumb UI components and intelligent agents.

05

Observability

The degree to which a system exposes its internal state to the environment.

Enables debugging, monitoring, and "glass box" user experiences.

06

Mutability

How a system's state changes over time (Immutable, Configurable, Mutable, Adaptive).

Helps us reason about state management and side effects.

07

Entitlement

The grant of a Capability to an Actor (User or Agent).

Decouples "what exists" (Registry) from "who can use it" (Policy).

08

Manifestation

The concrete realization of a Capability in the UI (e.g., a button, a command, a shortcut).

Allows us to track where abstract powers touch the user experience.

09

Surface Area

The set of all UI locations where a capability is exposed.

Critical for "UI Budgeting"—ensuring we don't overcrowd the interface.

10

Trait

A behavioral characteristic of a capability (e.g., "Destructive", "Long-Running").

Allows the UI to handle capabilities generically (e.g., automatically adding confirmation dialogs).

11

Registry

The immutable, central source of truth for all Capabilities definitions.

The DNA of the system.

12

Domain

A bounded context that groups capabilities (e.g., Dialogue, Landscape, Synthesis).

Organizes the system into coherent mental models.

13

Lifecycle

The evolutionary stage of a capability (Concept → Planned → Stable → Deprecated).

Communicates system maturity and roadmap transparency to the Thinker.

08

Concept Translation

We ground our architecture in established computer science and distributed systems theory.

HolonAdopted

Modeling components as recursive wholes/parts enables fractal architecture.

Systems Theory"Holarchy"

Applying service discovery patterns to internal application features.

Microservices Architecture"Service Registry / Catalog"

Granular permissions allow for precise composition of roles and agents.

Access Control Theory"Permission / Operation"

The system should be able to inspect and modify its own capabilities.

Lisp / Smalltalk"Reflection"

Shifting focus from "User Benefit" (Marketing) to "System Potential" (Engineering).

Product Management"Platform as a Product"

Mapping abstract capabilities to concrete perceptible affordances.

User Interface Design"Affordance"