InBody Auditor

The problem

I had every number. They never told me if I was okay.

• A scan prints a sheet. A sheet is not a story.
• I could not tell whether I was losing fat or muscle without doing the maths myself.
• Progress you cannot read is progress you cannot keep.

The real story · my data, all ten scans

Up, then down. The chart I could never see.

The year I lost

Then I stopped, and the sheet went red.

• Visceral fat doubled: 119.8 → 235.4 cm².
• InBody score crashed: 69 → 44.
• A year of sitting cost me more than the eleven months before it.

The claw back · Jun to Sep 2026

Five months later: fat down, muscle kept.

• 95.5% of the weight I lost was pure fat. Typical GLP-1 loss without lifting gives up 25–40% of it as muscle.
• Visceral fat down 17.2 cm². InBody score back up to 50.
• I only know any of this because I did the maths by hand. That is the bug.

What is actually missing

InBody already gives you the numbers. It does not give you your own story.

• Credit where it is due: the sheet already has a trend chart and change targets.
• What it does not give you is your history in your hands — it sits on paper, or inside the gym system.
• And nobody shares a result sheet. People share a chart with a sentence on it.

The sheet is data. The page is the story.

The market

Nobody wants another tracker.

• 17 lifting-positioned apps in the store, every one at 0–8 ratings.
• 602 reviews read. Half the complaints are not about features.
• 51% of negative reviews are paywalls — "free app but pay to use", "bait and switch".
• The pain is not missing features. It is that my own story sits behind a subscription.

So this is not a tracker. It is a translator.

The idea

Upload your scan history. Get back a plain verdict anyone can read:
how much you lost, whether you kept muscle, and your daily protein floor.

Model writes one coaching line. Page gets a fingerprint. One link, no subscription.

Live · the app's own output page

Chart, verdicts, protein floor, and a coaching line from qwen/qwen3.8-27b on Nosana. Served from a Daytona sandbox by signed URL.

How it works · three sponsors, all load-bearing

• 15-minute sandbox TTL, destroyed with wait=True.
• Why a sandbox for forty lines of maths? Because the input is a file I do not control.

Why me · every number checkable

I have already shipped to 100,000 people.

Spiko — Multilevel Prep · AI English Exam Prep

100,000+ installs on Google Play

4.7 stars from ~2,900 ratings · Uzbekistan

Cash-positive after infrastructure, inference and platform fees

play.google.com/store/apps/details?id=org.milliytechnology.spiko
verified on the live listing, 2026-09-19

Play shows a rating per country: 4.7 from ~2,900 ratings in Uzbekistan, where the app won — and 4.6 from 77 ratings in Korea, where it is new. Same app, same 100,000+ installs.

• That app won where the store still worked. This category is the opposite: 17 lifting apps, all at 0–8 ratings.
• And this is not a demo. Ten scans, two years, and a written plan to 68 kg — running on my own body.

Close

Thank you.

Appendix · for the code-level review

Where each sponsor lives in the source

• auditor.py · Daytona: create(), set_ttl(15), code_run(), delete(wait=True)
• serve.py · Daytona: serves the report with create_signed_preview_url(3000, 900)
• coach.py · Nosana: GET /v1/models to pick the model, then one chat completion
• publish.py · DNSimple: POST /zones/<zone>/records with the sha1 of the report
• analyze.py · stdlib only, the deterministic part

Appendix · likely questions

If they ask

• "Doesn't InBody already give you this?"
  The maths, yes — trend and targets are on the sheet. What it does not give you is your own history, in one link, that you own.
• "Why the sandbox?"
  The input is a file I do not control. For this workload it is more isolation than it needs, and I would rather say so than pretend forty lines of maths requires a cloud machine.
• "Is this a business?"
  No. It is a working demo of the positioning. My actual bet is a free-core GLP-1 app on a US beachhead.