Card Network Architecture: A Spatial Content System for the Agentic Web

Version 1.0 | December 2024

Abstract

Card Network Architecture (CNA) introduces a new paradigm for content representation where phone-sized cards serve as atomic units that stack, link, and network together. Designed for both human navigation and AI agent consumption, CNA provides structured, tokenized content optimized for edge computing and low-power devices.

1. Introduction

1.1 The Problem

Modern content systems face a fundamental tension:

1. Humans need visual, navigable, bite-sized content
2. AI agents need structured, tokenized, context-efficient data
3. Edge devices need minimal compute and offline capability

Current solutions (documents, wikis, databases) serve one audience poorly while optimizing for another.

1.2 The Solution

CNA resolves this tension through cards—atomic content units sized like a mobile phone screen (~250 tokens). Cards are self-contained, typed, connected, and efficient.

2. Core Concepts

2.1 Cards

A card is the atomic unit of CNA. Each card contains:

• Header: Title and optional icon
• Body: Content (text, code, media, actions, choices)
• Metadata: Tags, timestamps, token count
• Connectors: Visual attachment points for edges

2.2 Edges

Edges define relationships between cards with specific semantics:

• stack - Vertical sequence (A then B)
• link - Reference (A mentions B)
• embed - Containment (A contains B)
• branch - Conditional (if X, go to B)
• depends - Dependency (A requires B)
• produces - Output (A creates B)

2.3 Compositions

Compositions are named collections of cards and edges:

• Stack: Linear vertical sequence
• Network: Graph of linked cards
• Tree: Decision/navigation hierarchy

3. AI Optimization

3.1 Token Efficiency

Traditional content gets chunked into fragments, losing context. CNA cards are pre-chunked with preserved relationships. Each card is complete in isolation.

3.2 Graph Traversal

AI agents can navigate card networks without LLM inference. Follow typed edges to find related content programmatically.

4. Use Cases

• Documentation: Replace docs with navigable card networks
• Knowledge Bases: Enterprise knowledge as searchable graphs
• Educational Content: Courses as card compositions
• Agent Context: Structured context for AI agents

5. Conclusion

Card Network Architecture bridges the gap between human-readable content and machine-efficient data. By treating cards as atomic units connected by typed edges, CNA enables efficient AI agent context, edge device deployment, and intuitive human navigation.