Hands-on engineering evidence

AI Engineering Lab

A focused set of practical systems showing how I turn messy domain knowledge, files, videos, and workflows into searchable, testable, and reusable AI-assisted tools.

Why this matters for an AI engineer

These projects show that I work close to code, data, evaluation, automation, and delivery—not only at the architecture or strategy layer.

Lab Projects

Knowledge ManagementSearchable DocsRAG-ready Content

Game Engine Knowledge Base

Organizing 996 / Mirserver / Legend engine materials into a structured, searchable knowledge base that can support future retrieval, documentation, and assistant workflows.

What this proves

Shows the ability to turn fragmented domain knowledge into governed data assets and AI-ready content systems.

Representative outputs

  • Directory inventory and source map
  • Searchable topic index
  • Engine terminology and configuration notes
AutomationRule CheckingLuaConfig Governance

Game Config & Lua Analysis Toolkit

Batch analysis for NPC, item, BUFF, Lua, and configuration files to detect issues, explain logic, and produce maintainable technical notes.

What this proves

Shows practical engineering of operational rules, validation logic, and domain-specific developer tooling.

Representative outputs

  • Config scanning scripts
  • Lua / NPC / item analysis reports
  • Error explanations and change notes
OCRContent AutomationMarkdownCourse Production

Video-to-Documentation Pipeline

A workflow for turning course videos into structured written tutorials through frame extraction, OCR, chapter organization, and Markdown generation.

What this proves

Shows the ability to convert unstructured media into reusable learning assets with measurable production efficiency.

Representative outputs

  • Extracted key frames
  • OCR JSON outputs
  • Generated Markdown course documents
AI-native DevelopmentCodexClaudeGitVercel

AI Coding Workflow Playbook

A practical operating manual for using AI coding agents to decompose requirements, build prototypes, debug code, manage Git workflows, and deploy web products.

What this proves

Shows that I can teach and operationalize AI-assisted development instead of only using tools ad hoc.

Representative outputs

  • Zero-to-one AI coding tutorials
  • Git collaboration commands and scripts
  • Next.js / Vercel deployment notes

From experiments to production systems

The lab work uses the same engineering pattern as the enterprise cases: structure messy inputs, define reliable workflows, add AI where it helps, verify the outputs, and package the capability for reuse.