Benny Cheung is a software engineer and AI enthusiast focused on building intelligent systems and agent-driven workflows. His writing covers AI agent orchestration, edge AI, local-first architectures, and AI-powered automation for real-world applications.
15 articles from this blog
Explores using AI and LLMs to automate board game playtesting, analyzing balance, skill gaps, and rule clarity without human testers.
Explores Generative Ontology, a framework using structured game knowledge to guide AI in creating novel tabletop game designs.
Explores how AI hallucinations mirror Kant's philosophy of mind, arguing they are inherent to rational thought architecture, not software bugs.
Introduces Nova, an AI co-designer for board game creation that learns a designer's preferences and remembers past decisions through conversation.
Introducing GameGrammar, an AI system that uses six specialized agents to generate complete board game designs from a simple theme in seconds.
A guide to converting NotebookLM's uneditable PDF slides into fully editable presentations using a 4-tool pipeline involving Canva, Google Slides, and AI.
A guide to adding voice notifications to Claude Code AI agents using hooks, a local server, and ElevenLabs TTS for ambient awareness of parallel tasks.
Case study on building an edge AI food monitoring system using AI-led development with the BMAD framework, achieving rapid delivery with minimal human oversight.
A guide to building an offline, edge AI food monitoring system using a Raspberry Pi, YOLO11, and a local-first architecture for privacy.
A technical comparison of YOLO-based food detection from 2018 to 2026, showing the evolution of deep learning tooling and ease of use.
A technical workflow using AI to transform hand-drawn mind maps into searchable, shareable digital visualizations in a consistent illuminated manuscript style.
Proposes a new AI agent architecture based on Alfred North Whitehead's process philosophy, treating agents as dynamic processes rather than static entities.
A technical guide on integrating two distinct AI agent systems (BMAD and PAI) using a layered architecture to combine their strengths.
Explores Abstraction of Thought (AoT), a structured reasoning method that uses multiple abstraction levels to improve AI reasoning beyond linear Chain-of-Thought approaches.
Explains how a semantic ontology model acts as a 'queryable brain' to understand, document, and confidently modernize complex legacy software systems.
