AI - Glow Journal

Everyone building AI health tools is copying the same architecture:
user uploads image → cloud API → result returned.

Looks clean in a demo.
Falls apart economically at scale.

I went a different direction with my skin health app.

TFLite model runs entirely on-device:

• No per-call inference cost

• No latency

• No privacy concern about images leaving the phone — because they don't

A few things I figured out the hard way:

On-device inference changes your unit economics permanently

When the model runs locally, your cost per scan is $0 — regardless of volume.

That’s not a small detail.
It’s the difference between a viable consumer product and one that gets squeezed by its own growth.

Privacy-by-architecture beats privacy-by-policy

“We comply with GDPR” is a legal statement.
“Your scan runs on your phone and never leaves it” is a product statement.

Users respond very differently to the second one.

The AI model is not the moat

Anyone can fine-tune a skin analysis model.

What actually takes time:

• Two-sided dermatologist marketplace

• Patient data sharing

• Async consultations

• Subscription tiers

• Admin tooling

The model is maybe 10% of the real product surface.

$0/month infrastructure is a strategic choice, not a limitation

Full stack running on:

• Google Sheets

• Apps Script

• Cloudinary

• Netlify

The right question isn’t “can it handle 10M users?”
It’s “can it reach the point where you can afford to migrate?”

Yes. Easily.

Curious if anyone else building health or wellness AI has hit similar decisions — especially around on-device vs cloud inference tradeoffs.

What pushed you one way or the other?

(If you want to see the actual build — Flutter, full derm booking marketplace, $0/mo infra — I posted about it separately. Happy to answer architecture questions here too.)

Hey IH,

I'm selling Glow Journal — a fully built, production-ready skin health app I built as a side project.

What it is

A three-sided skincare marketplace — patients, dermatologists, and admin.
Users scan their skin with on-device AI, track their glow score over time, book appointments with dermatologists, follow personalised routines, and shop skincare products.

The honest pitch

I'm a solo developer with no funds to market and scale it.
I'd rather hand it to someone who'll launch it than watch it sit on my drive.

Tech stack (all free)

• Flutter (iOS + Android + Web)

• Google Sheets as database

• Google Apps Script as REST proxy

• Cloudinary for image storage

• TFLite on-device AI — zero cloud cost

• Netlify for admin panel

What's built

Patients:
AI skin scan, glow score, history charts, derm booking, routines, skincare product marketplace with AI recommendations, skin diary, cycle tracker, ingredient checker, challenges, community gallery, subscription tiers (Free / Pro / Premium)

Dermatologists:
Verified profile, patient portal, booking management, shared scan data, messaging, analytics, clinic features, subscription tiers (Free / Professional / Clinic)

Admin:
User management, derm approval/rejection, booking overview, broadcast notifications, content management, product listings management, revenue analytics

Revenue streams (all wired in)

• Patient subscriptions (Free / Pro / Premium)

• Dermatologist subscriptions (Free / Professional / Clinic)

• Booking commissions

• Skincare product marketplace (affiliate-ready)

• Clinic B2B licensing

• AI data licensing

Backend cost: $0/month

Three tiers

$10,000 — Code-Only (firm)
Complete codebase, immediate handover. No negotiation on this price.

$15,000 — Launch-Ready
Code + published on Play Store & App Store + live Stripe payments. Delivered in 2 weeks.

$25,000 — Scale-Ready
Everything above + real database migration. Supports 100K+ users. Delivered in 3–4 weeks.

Why that price

A Flutter dev quoting this from scratch would charge $40,000–$80,000.
You are buying 6–12 months of senior development work starting at $10,000 — with $0/month infrastructure cost from day one.

Interested?

Drop a comment or email iqbal_nazar@hotmail.com — happy to do a screen-share walkthrough.