Shelf scan
Review a barcode scan with an item record and a Confirm quantity field.
Back to work
- Small shop inventory
- AI mobile concept
Stockpiper
A shop-floor inventory companion for label capture, catalog cleanup and source-backed stock questions.
Designed around4 AI workflows
Project overview
Stockpiper explores small shop inventory through a mobile experience built around a barcode-first stock screen with large one-handed actions. A shop-floor inventory companion for label capture, catalog cleanup and source-backed stock questions. The proposed journey connects shelf scan, catalog cleaner, ask stock notes, count session. Four original phone showcases establish the visual direction, while the case study defines the supporting feature set and a proposed Java architecture.
The challenge
Shop staff need scanned labels, voice notes and item records connected while proposed stock changes remain explicit. On a phone, the person also needs to capture information quickly, understand where an answer came from and return to the original material without navigating through a dense desktop interface.
- Keep shelf scan and catalog cleaner connected within a short mobile flow.
- Make label reading correctable when the model misreads the input.
- Explain inventory retrieval through visible references or user-selected preferences.
- Keep changes, sharing and data retention under explicit user control.
Our solution
The design begins with a barcode-first stock screen with large one-handed actions, using large touch targets, short task sequences and contextual sheets. Extract candidate item fields from packaging labels. Suggest consistent titles and categories for approval. The companion views keep drafts, original material and accepted decisions distinct. A indigo, mint and cream visual system gives this app its own character within the collection.
- Extract candidate item fields from packaging labels.
- Suggest consistent titles and categories for approval.
- Answer questions from recorded stock data with source entries.
- Group unresolved count notes without automatically changing quantities.
Key features
Inside the platform
Turn a shelf check into a clear record.
Original mobile interface concepts with fictional content. AI responses illustrate proposed interactions; they are not live model results.
Proposed technology stack
Proposed Android architecture using Java and Android Views. AI processing, storage and synchronization are design proposals for this concept, not integrations implemented by this portfolio.
- Java
- Android Views
- SQLite
- AI services
The results
The concept defines four mobile views, four AI workflows and twelve feature areas. The next validation would ask a user to complete shelf scan, inspect the proposed catalog cleaner output and correct an intentional extraction or suggestion error. Evaluation would focus on source traceability, correction effort and task completion. No usability study or business-impact measurement is claimed.
4Original mobile showcase views
4Proposed AI workflows
12Designed feature areas
Ready to build something similar?
Let's bring your idea to life
Whether it's a platform for your industry or something completely different, we can help you build, integrate and scale.