The Real Ambient Scribe Question is Trust, Not Note Quality

I built a browser-based AI medical scribe as a way to explore whether the real question isn’t just “can AI write a good note?” but “can it be done in a way that feels more private and trustworthy?” The idea was to keep everything local-first in the browser rather than relying on a backend, covering transcription, summarisation, review, and structured output in one place. It’s not a finished or clinical product, but it clarified where the real challenges are. Privacy is only part of it, reviewing and trusting the output still takes effort, and the hardest problem is often getting that output back into real healthcare systems in a useful way.