Essays on spec‑driven development, AI in clinical practice, and what I've learned building at the edge of medicine and software. Cited primary sources, honest confidence flags.
Every post here follows the same rule: claims are grounded in primary sources (clinical guidelines, FDA guidance, peer‑reviewed literature) or flagged as personal opinion. If a sentence would surprise me coming from a stranger, I cut it or cite it.
Between the hype of autonomous clinicians and the reality of locked-down hospital IT is a much narrower, more interesting corridor. A grounded look at what's shipping, what's FDA‑cleared, and where the useful work actually sits.
Read the essayA workflow for clinicians, researchers, and analysts who want to use AI as a force multiplier, not a toy. Spec‑driven prompting, multi‑chat orchestration, verified outputs. Actionable from day one.
Read the essayOpen‑ended prompts produce debt. Locked prompts produce verifiable output. Notes from ~12 months of building real software with Claude Code, with the prompt patterns that worked and the ones that didn't.
Read the essayWorking on something at the intersection of AI and healthcare?
Get in touch