Health, home and travel decision
FishingAI
A competent developer can reproduce the core photo+weather->lure recommendation and a personal catch log using off-the-shelf vision and weather APIs, but matching the polished native iOS UX, App Store billing integration, and any proprietary model/data would be costly—so build a narrow replacement but keep paying for the full product if you need the complete mobile experience and polish.
View on the App Store↗$1.67/mo
$20/yr
Read off the official pricing page.
$100one-off96 h to build
$50/mo6 h/mo upkeep
On cash alone, building overtakes the subscription at 35 seats.
No open-source build does this yet
Nothing published replaces this one, so a replacement starts from an empty file. Here is what it would have to cover.
What a replacement has to do
- User photographs fishing spot -> analyze image + fetch weather/conditions -> produce lure recommendation -> save to personal catch log
What it still won’t have
- Polished native iOS camera UX and App Store distribution polish
- Integrated, curated lure database and any proprietary recommendation tuning
- Existing user base, ratings and reviews
- Push notifications and tight iOS-specific integrations
- Any proprietary models or training data used by the vendor
What remains hard
- Product polish and ongoing maintenance
First-year cost
Keep paying
Paying is—cheaper in year one.
On cash alone, building overtakes the subscription at 35 seats.
Money you would actually spend
Time you would spend
—
What you would spend
What we assumed
The verdict above measures whether you could build it. This one is only about money.
Runnable build prompt
Build a minimal web+mobile-friendly fishing assistant using Node.js (Express) backend, PostgreSQL, React frontend (or React Native for simple iOS support), and hosted on Vercel (frontend) + DigitalOcean App Platform (backend) or Heroku. Core features in scope: 1) mobile camera upload endpoint and simple React/PWA UI for taking photos, 2) server endpoint that calls a hosted vision API (e.g., OpenAI/available vision model or AWS Rekognition) and a weather API (e.g., OpenWeather) to produce lure suggestions via rule-based mapping, 3) user account + subscription check (Stripe) to gate premium features, 4) catch log CRUD stored in Postgres and UI to view past analyses, 5) basic analytics for catches and export as CSV. Out of scope: native iOS App Store packaging and App Store in-app purchase flows beyond Stripe-hosted billing, advanced proprietary model training, offline mode, and push notifications. Include input validation, error handling, unit tests for backend endpoints, and an integration test that exercises the photo->recommendation flow.
How we checked
How the score was reached
- Partly verdict base52
- Price verified on pricing page+3
- 3/3 assessment runs agreed+4
- Evidence score59
The base comes from the verdict. Everything under it is a check that either happened or did not, and each one is a fact frozen in this record rather than a judgement made at render time - so the same evidence always produces the same number.
How scoring works →Integrity checks
What held up, and what did not.
