Image and video decision
Car Identifier
A technically competent developer can reproduce a usable car-identification workflow by wiring a client UI to an off-the-shelf vision API plus a small specs database, but matching the vendor’s data quality, mobile polish, and App Store presence requires more effort and nontechnical assets.
View on the App Store↗$9.99/mo
$120/yr
Per seat. Read off the official pricing page.
$100one-off70 h to build
$50/mo4 h/mo upkeep
On cash alone, building overtakes the subscription at 6 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 takes or uploads photo → run car-recognition model → map prediction to car-specs database → show results and allow save to collections → store history and allow filtering
What it still won’t have
- Access to the vendor’s proprietary labeled training data and any bespoke model tuning
- Polish of the production mobile UX and incremental updates/releases
- Existing App Store presence, ratings, and brand trust
- Potentially large curated specs dataset and any paid licensing the vendor may use
- Integrated analytics and crash handling configured 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 6 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 iOS Car Identifier app using SwiftUI + a small Node.js (Express) backend on a single small cloud VM. Core features in scope: photo capture/upload, call an external vehicle-recognition inference API (e.g., hosted vision model) and parse make/model/year with confidence, map predictions to a local car-specs table (SQLite on the server) and return speed/0-60/price/production years, save per-device user collections and history (simple token-based auth), implement StoreKit subscription gating for identification and saving, search/filter history and brand-logo collection, and a responsive result UI. Out of scope: training custom ML models, large-scale analytics, multi-tenant billing, and advanced ranking. Include error handling for network and inference failures, input validation, automated unit tests for backend endpoints, and basic CI to run tests.
How we checked
How the score was reached
- Partly verdict base52
- 2 cited sources+1
- Price verified on pricing page+3
- 3/3 assessment runs agreed+4
- Evidence score60
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 →Cited sources · 2
Every page the run actually retrieved.
- official productCar Identifier: CarSnap - App Store
- official pricingCar Identifier pricing and in-app purchases (excerpt)
Integrity checks
What held up, and what did not.
