Prompting has a ceiling. Once you hit it, you are coordinating every step manually while the AI handles individual tasks. Here is the framework and three live workflows I use to cross that line.
After six weeks of missed training, my PGIS morning check-in revealed what a GPS watch alone never shows: glycemic and autonomic recovery run on entirely different clocks.
PGIS Recipes started as a stack of Marp slide decks. I turned it into a GitHub Pages library because nutrition guidance only compounds when the delivery system is structured, durable, and easy to revisit.
Before you build any AI feature, you must first build the log. The principle every physician-developer needs to internalize before writing a single line of intelligence code.
A physician-developer explores the powerful parallels between AI-driven glycemic control in the ICU and metabolic management for endurance athletes with Type 2 diabetes, introducing the Performance Glycemic Intelligence System (PGIS) as a real-world n-of-1 framework.
A Maternal-Fetal Medicine specialist describes how his personal AI health system identified low HRV, recommended breathing exercises, and prompted him to build a custom evidence-based breathing app in a single afternoon. A case study in disposable software, physician agency, and the future of personal health technology.
Maternal-Fetal Medicine Specialist | Founder, CodeCraftMD | Atlanta Perinatal Associates