These products / projects, some are public tools, some are research traces, and some are small systems that helped me understand a problem better.

They are a map of recurring interests: healthcare, AI, knowledge systems, teaching, and the practical work of making complex things clearer.

Open source releases

Recent public tools focused on Taiwan healthcare knowledge infrastructure, source-cited lookup, and AI-ready document pipelines.

OpenTaiMed / taiwan-fda-mcp

An MCP server for trustworthy Taiwan drug-information lookup. It wraps the official TFDA APIs so AI assistants can fetch package inserts and drug-license data instead of guessing.

  • Status: shipped — taiwan-fda-mcp on PyPI (v0.2.1)
  • Why it exists: to make AI answers trace back to official TFDA text
  • What it connects: clinical pharmacy, official drug data, MCP clients, and source-cited assistant workflows

nhi-knowledge-extractor

A pipeline that converts Taiwan NHI medication regulation documents into RAG-ingestion-ready CSVs. It preserves hierarchy, reads tables directly, and keeps the token budget under control.

  • Status: released
  • Why it exists: to remove repeated manual fix-ups from each NHI update cycle
  • What it connects: healthcare regulation, structured document parsing, RAG ingestion, and reproducible data pipelines

Healthcare knowledge systems

Work shaped by pharmacy practice, medication knowledge, and the need for clear clinical information at the right moment.

Hospital Formulary

A digital formulary knowledge base created from hospital pharmacy practice.

Hospital Formulary screenshot

Why it exists
I wanted medication information to be easier to search, maintain, and explain in daily clinical work.

What it connects
Clinical pharmacy, knowledge organization, documentation, and healthcare workflow design.

What I learned
Good information systems are not only about storing facts; they are about reducing friction at the moment of decision.

Research and presentations

Research traces, posters, talks, and other artifacts from trying to understand healthcare problems more clearly.

Scientific Poster at ASHP 2023

Effect of an improved antimicrobial stewardship program at a regional hospital in Taiwan.

ASHP 2023 poster screenshot

AI and automation experiments

Small systems and prototypes around healthcare AI, retrieval, documentation, and workflow automation. Some are public; many are still private, internal, or evolving.

  • Medical AI / RAG experiments — exploring how retrieval and language models can support clinical knowledge work without replacing clinical judgment.
  • Documentation automation — using software to reduce repetitive writing and make healthcare documentation clearer.
  • Paper discovery and review workflows — systems for finding, reading, and preparing research for journal clubs and presentations.
  • Agentic workflows — experimenting with AI agents as helpers for research, coding, note review, and task orchestration.

Learning and personal systems

Systems I use to think, remember, review, and decide what deserves attention.

  • Obsidian knowledge system — notes, daily logs, research fragments, project planning, and periodic review.
  • Daily and weekly review routines — small practices for turning scattered tasks and thoughts into clearer next actions.
  • Reading and paper notes — a growing habit of translating what I read into reusable understanding.
  • Website as a personal home — this site itself is also a project: a quieter place to gather what I’m learning, building, and becoming.

Teaching and community

Projects are not always software. Some are formats for sharing, explaining, and learning with other people.

  • Clinical teaching — helping learners connect pharmacy knowledge with real patient-care decisions.
  • AI and healthcare education — preparing explanations, workshops, and journal club materials for mixed clinical and technical audiences.
  • Book clubs and study groups — creating spaces where people can read, ask better questions, and learn together.

Status

This page is intentionally incomplete. I expect it to change as old projects become clearer, private experiments become shareable, and new questions start to matter more.