You can see my body stats while I sleep

You can see my body stats while I sleep. It is the first thing on the homepage: a live chart of my glucose, sitting behind the sentence about what I build, still updating at 3am when I am not performing for anyone.

I thought it would be cool and unique. I have spent a long time in healthcare, where the default is to treat personal information like a biohazard. That secrecy makes sense when it is someone else’s chart. This is my PHI, so why not share it?

I wanted the site to read like it belonged to somebody who lives in this body. I meet the definition of a cyborg: a sensor on my arm, a pump, an open-source loop dosing insulin every few minutes. The homepage just makes that visible: live body stats, including while I sleep.

My A1c teeters around 4.9% to 5.0%, and that number does not tell you what the lows feel like. I have not really shared how I got there. I am starting with the technology I use and what I am building. Fair warning if you stare at it long enough. A normal lunch is a bump. A meal I forgot to bolus is a real spike (oops, whoopsie doodle). Sometimes I sleep on the sensor and you get a compression low, and sometimes the line cliffs to 250 in minutes, out of nowhere. That last one is the sensor falling apart, not my afternoon.

The number was already there

Dexcom and DIY Loop have been writing a point every five minutes for years; I already had the history. I needed the public page to show whether its data was current without putting the endpoints my providers use on the public internet.

If the feed is old, the page has to say so. Stale data can stay on screen; it cannot pass as live.

The public site does not talk to Nightscout. A Cloudflare Worker sits in front, caches the last stretch, and serves /api/glucose from this domain. The browser only ever hits my site, so the endpoints my clinicians use do not get hammered because someone left the homepage open overnight.

I did not hesitate. The models did.

I put my own glucose data on a page I own without hesitation. The AI agents doing the work almost refused. They turned a manageable build into a fight over whether I was allowed to.

Claude, at least with Opus 5, was a pain in the ass for this. The fucking verbosity turned into overcomplicated phrases and mind-bending detours. Four to six hours going over the top on everything. Then the healthcare refusals started: “that’s a bit I can’t do,” “that’s a line I can’t cross,” even with me sitting there saying this is my data and I am authorizing it. I have liked Anthropic’s work for years. These newer models made the job harder, so I cancelled the subscription and moved to Cursor Ultra for work and home.

Codex and Grok, in Cursor, took the request. Got it boss, working on it now. Then they showed me screenshots and a recording.

The models kept trying to add more: extra chrome, another widget, a little glow so it feels “alive.” I ranted into speech-to-text for a good minute and got an instrument instead of a health-app hero. Engineers should use STT more because it lets you dump the thought before you clean it up.

This is the prompt I keep using through Paseo:

Dispatch 3 finely scoped agents to design mock-ups of the idea. Single artifact, HTML/CSS/JS only. Show me, then I will pick what I like about each and put them together. Use Playwright for screenshots.

I run these agents through Paseo from my desk or phone, then I pick what stays. I used the same process for the diagrams in this post. Show me the object.

Same day, two drawings

The clock on About came later. It draws the same feed differently. I put a 24-hour loop of my body under the intro because that page is about me.

I just build things now

I build things that make me happy. If I can say the idea clearly, I do not wait around for a free week; I can ship the concept, or even the whole piece of software, in minutes or hours instead of days.

I will write about the full protocol behind a 4.9 separately; the chart is already on. Go look.