Build your own Yuka.

# Build an original app inspired by Yuka

You are an experienced mobile product designer and mobile engineer. Build a working, polished MVP from the brief below. Implement the core journeys end to end; a static mockup is not sufficient. Inspect the current environment, make sensible implementation decisions, and get started. Ask a question only if a missing answer genuinely blocks implementation.

Starting platform: iOS / Android. Explicit customized Product & audience and Tech stack requirements take precedence over this starting target.

## Product & audience
Build an original native food-label companion called Labelwise, inspired by Yuka’s scan-and-inspect workflow. It is for shoppers viewing ingredient and nutrition information for a small permitted product catalog. The primary journey is scanning or typing a barcode, inspecting a source-labeled product record, and saving it for comparison. Deliver iOS/Android projects with a real scanner; do not invent a health rating or imply access to Yuka’s private database.

## Design
Use an original scanner screen with a clear camera frame, manual-entry alternative, and a readable product facts page. Show data source, update date, measurement basis, and missing fields. Comparisons use labeled values rather than unexplained red/green health verdicts. Support text scaling, screen readers, sufficient contrast, and accessible permission/error messages.

## Features
1. Barcode input: request camera permission when scan is chosen, read supported retail barcodes through a maintained native camera/scanning plugin, validate format, and debounce repeated detections. Provide manual barcode entry and stop the camera when navigating away or backgrounding.

2. Product lookup: match against a bundled original test catalog first; optionally query a documented permitted external provider only when configured. Show loading, not-found, stale-cache, and network-failure states separately. Unknown products must not produce a fabricated name or rating.

3. Label facts: show ingredients and available nutrition per 100 g/ml or per serving with units and source attribution. Highlight user-selected ingredient terms only as literal label matches, with an explanation that missing data is unknown and the app cannot confirm allergy safety.

4. Compare and history: save scanned products locally, select two to compare like-for-like values, and distinguish incompatible units or incomplete fields. Allow favorites and deletion of history. Never rank a product as medically safer based on invented data.

5. Offline and portability: open cached products without a connection, identify the cache timestamp, and let users clear it. Export scan history as an app-owned JSON through native sharing. Include a usable test barcode sheet with permitted sample products for scanner verification.

## Tech stack
Use Flutter/Dart with native iOS/Android project directories, SQLite, and a maintained scanner plugin backed by platform camera APIs. Configure camera usage descriptions and lifecycle cleanup. Isolate product lookup behind an adapter, keep API credentials server-side if a provider requires secrets, and verify its current data license/attribution before use. The bundled edition needs no network credentials. Do not use a WebView or scrape Yuka; no server or account is needed for local history.

## Data & behavior
Product {barcode, name, ingredientsText, nutritionBasis, nutrientValues, units, sourceURL, license, sourceUpdatedAt, fetchedAt}; ScanEvent {id, barcode, scannedAt}; Favorite; IngredientPreference; CatalogVersion. Preserve unknowns as null, normalize units only through documented conversions, and keep provider data separate from user notes. Use bounded request/cache sizes, validate external responses, and store no camera frames by default. Resolve a lookup only if it still belongs to the active scan.

Acceptance checks and scope:
Scan a permitted known barcode, scan an unknown one, deny camera access, and use manual entry. Compare products with different serving bases, inspect missing sodium/ingredients, background the scanner, and reopen cached records offline. Test network retry, malformed responses, rapid duplicate scans, and native builds on both targets; state physical-camera verification limits. Exclude copied scoring formulas, cosmetic safety analysis, diagnosis, medical recommendations, allergy guarantees, commercial catalogs without permission, and automatic purchases.

## Originality and assets
The named product is a reference for general workflows only. Use an original product name, visual identity, wording, layout, and assets. Do not copy proprietary code, branded logos, distinctive screens, private APIs, paid templates, or protected media. Use original or appropriately licensed sample data and assets. Build from this brief rather than scraping the reference service. Do not imply affiliation with the referenced company.

## Implementation quality
- Make every visible control work, with clear loading, success, empty, validation, and failure states. Remove controls for unimplemented features.
- Support the target platform and responsive or resizable layouts where appropriate. Use platform-appropriate accessibility semantics, labels, keyboard operation, visible focus, sufficient contrast, and reduced-motion preferences. Provide alternatives for drag-only interactions.
- Validate inputs at the relevant boundary. Treat imported or user-generated content as untrusted; render it safely. Confirm destructive actions or offer undo.
- Keep state changes reliable across navigation and reloads. Never silently lose edits. Handle persistence and network errors with an actionable message.
- Keep the scope realistic. Prioritize the complete primary journey. If a custom Features section differs from the baseline, update the data model, design, and acceptance checks to match it; explicit custom requirements take precedence over baseline assumptions.
- Provide realistic original sample content and a useful empty state. Keep sample data clearly separate from user-created data.

## Delivery and verification
1. Inspect the repository and outline the implementation in a few sentences.
2. Implement the app and connect its actual data flow. Continue until the primary journey works.
3. Run appropriate checks and test the acceptance cases above on the target platform. Verify responsive layouts and keyboard navigation when browser tools are available. For native projects, build with the available SDK and test an emulator or device when possible; report any missing native verification honestly. For games, verify the rules and gameplay loop, not only the menus.
4. Fix observed failures, then provide the runnable result, setup/run instructions, a brief explanation of what is implemented, and any specific configuration or verification limits.

This is a focused MVP. Do not add billing, AI services, or unrelated features unless explicitly requested in the brief. Start building now.