Hi, I'm Michael! 👋
I am still alive. I'm just an ordinary person living in a boring world. But I am passionate about things like computers, space, science, engines, robots, artificial intelligence, books, etc. I want to create a world, an era, an environment where humans and artificial intelligence can live under the same sky. And I also want to build a house for my parents. My dream is to help the blind, the disabled, autistic children, or those struggling with technology by applying artificial intelligence to their lives to make their lives better. (❁´ ◡` ❁)
Currently, I focus on building practical AI systems, automation, and software products — especially solutions that can help businesses operate more efficiently and better support people, from workflow automation to computer vision and child-safe AI experiences.
Selected Work
Learn more-
MoYi Edge Translation
An on-device AI translation runtime for multilingual operations where context, domain terminology, and safety messages matter more than sentence-by-sentence translation.
→ -
Sandora
An AI Department OS for building virtual AI teams, automated workflows, and human-governed business operations.
→ -
Autopilot & FSD - BFMC
A ROS catkin autonomous driving stack for Bosch Future Mobility Challenge 2024/2025.
→ -
Dossier
A local-first Agentic Document Intelligence platform that turns sensitive documents into reviewable, approved, and integration-ready structured data.
→ -
Pharmaceutical QC Defect Detection Machine
Computer vision system for detecting defects in pharmaceutical blister packs.
→
Recent Writing
Learn more-
Designing a safe AI companion: having memory while remaining controllable
An AI companion with memory doesn't just mean saving as much as possible. For safety, we need to clearly design what memory is saved, who can view it, when it's deleted, and when humans must be brought into the control loop.
→ -
Snow AI Companion: what to consider when designing child-safe AI?
A design note for Snow AI Companion: if AI targets children, especially those needing support in communication and learning, the product must start with safety, control, and gentle companionship.
→ -
AI Agents shouldn't start with agents, but with workflows
Before talking about AI Agents, tool use, or autonomous systems, we should start with a real workflow: who does what, where the data is, what steps need automation, and what steps need human control.
→ -
Why AI Engineers need to understand business workflows, not just models
An AI Engineer doesn't just need to know prompts, RAG, or models. To create real value, they must understand the workflow, data, users, and how the system operates in practice.
→