Personal medical knowledge base
A workflow for turning textbooks, papers, and AI-generated summaries into a searchable local knowledge base.
Project notes
Projects
These are not portfolio case studies. They are ongoing knowledge systems: tools, habits, and experiments that turn reading, clinical learning, and AI work into durable output.
A workflow for turning textbooks, papers, and AI-generated summaries into a searchable local knowledge base.
Project notes
Customizing coding agents so they can work with Zotero, Obsidian, PDFs, and medical reading workflows.
Project notes
Apr 18, 2026
Apr 23, 2026
Understanding modern AI applications by reading and modifying TypeScript-heavy agent projects.
Project notes
Apr 18, 2026
May 28, 2025
Using public notes to make scattered decisions, anxieties, and experiments visible enough to improve.
Project notes
May 26, 2025
Dec 12, 2025
Nov 29, 2025
GitHub projects
A selected map of repositories that connect the writing here to actual code: medical AI systems, local-first health tools, clinical data workflows, and research experiments.
Evidence-based medical Q&A system that combines local medical textbooks, ChromaDB retrieval, PubMed search, and MedGemma answer generation.
Privacy-first chronic medication management app for reminders, adherence tracking, health measurements, refill alerts, and local backup.
A lightweight bedtime companion focused on one nightly path: tonight plan, breathing, soundscape, phone down, and morning review.
TypeScript clinical data cleaning system with quality scoring, duplicate handling, missing-value strategies, audit trails, API, dashboard, and CLI.
Clinical cardiovascular prediction experiments comparing tabular-to-text Transformers, LLM in-context learning, and traditional ML baselines.
Real-time cardiology outpatient documentation system connecting ESP32-S3 audio capture, medical speech recognition, MedGemma reports, and physician review.
Project map
AI is not just a topic here; it is the practical lever that turns uncertainty into experiments.
The recurring pattern is simple: build first, then use the friction to discover what must be learned.
The medical thread is about making knowledge usable: searchable, testable, and close to real work.
Writing is the method for making thought visible, and action is the test that keeps thought honest.