Harness engineer dedicated to building the engineering environments and systems that enable AI Agents to produce high-quality code efficiently and reliably. Pursues minimalism and explores lightweight frontend approaches.
Previously led search engine and foundational data center services at Epic Games, with deep experience in search architecture and large-scale data processing.
Representative projects include Visual Replay Tester (next-generation desktop automation testing tool), Neuro-IDE (WYSIWYG desktop automation testing IDE), AILock-Step (MCP-based AI Agent execution protocol), and Feature Workflow (an AI workflow fusing BMAD and OpenSpec).
Feature Workflow v3 upgrades to a Command + Agent + Skill three-layer architecture. The core insight: template-based workflows are not silver bullets — every project needs purpose-built Skill design.
Exploring the core of Agent-First transformation: Skill codification, security design, and commercialization methodology, drawing from cross-border e-commerce practices.
A strict linear execution protocol based on STP state anchors. Eliminates hallucination skipping via physical jumps, enabling checkpoint-resumable AI Agent development with absolute idempotency.