Research
Deep insights into Software 3.0, AI architectures, and the future of human-computer interaction. Our research explores cutting-edge developments in LLM systems, dynamic software generation, and revolutionary computing paradigms.
The Agentic Framework: Beginning
The tip of the iceberg: An introduction to the three-layer Agentic Framework. This beginning explores a single Act of Thoughtful Doing, setting the stage for deeper dives into Actionable Knowledge, recursive agent interactions, and the methodology of building good Agents.
Building Anthropic Artifacts for Claude Desktop: An MCP Integration Experiment
Testing the new Anthropic Artifacts feature with a complex MCP integration. We built a visual workflow orchestrator for video generation, uncovering both the promise and current limitations of AI-powered app creation.
Beyond Chat: The Interface Patterns Shaping Human-AI Collaboration
Examining seven distinct interface patterns that have emerged across the AI landscape. From canvas-based visual workflows to headless automation, each pattern represents a different philosophy about how humans should direct AI capabilities.
Code AND No-Code: The Three Layers of Software 3.0
When Natural Language Orchestrates Algorithms Through Constructive Thinking. The evolution from Software 1.0 through 2.0 brings us to Software 3.0—a synthesis that transcends the false dichotomy of code vs no-code.
GTUI: When Interfaces Converse Themselves Into Existence
The evolution from autocomplete to auto-interface. How GTUI creates a new interaction paradigm bridging natural language conversation with dynamically generated visual interfaces.
The H2A Manifesto: From Code to Conversation
How AI is revolutionizing software development through natural language programming and the emergence of Software 3.0. A personal journey from non-programmer to AI orchestrator.
MCP Architectures for Video Creation: Monolithic vs Microservices
A comprehensive analysis of two architectural patterns for building AI-powered video creation workflows using the Model Context Protocol. Explores trade-offs between custom-built monolithic systems and pre-built MCP microservices.