Memory capture
Review an old photograph scan with crop handles and editable date uncertainty.
Back to work
- Family photo stories
- AI mobile concept
Keepselia
A family-memory app joining photo scans, voice stories and private collaborative albums.
Designed around4 AI workflows
Project overview
Keepselia explores family photo stories through a mobile experience built around an editorial memory timeline with large photo cards. A family-memory app joining photo scans, voice stories and private collaborative albums. The proposed journey connects memory capture, story conversation, archive search, family album. Four original phone showcases establish the visual direction, while the case study defines the supporting feature set and a proposed Swift architecture.
The challenge
Photo collections need dates, spoken memories and family corrections to remain traceable as stories are assembled. 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 memory capture and story conversation connected within a short mobile flow.
- Make photo description correctable when the model misreads the input.
- Explain archive retrieval through visible references or user-selected preferences.
- Keep changes, sharing and data retention under explicit user control.
Our solution
The design begins with an editorial memory timeline with large photo cards, using large touch targets, short task sequences and contextual sheets. Suggest descriptive captions without identifying unknown people. Turn a contributed recording into an editable narrative. The companion views keep drafts, original material and accepted decisions distinct. A sage, warm white and copper visual system gives this app its own character within the collection.
- Suggest descriptive captions without identifying unknown people.
- Turn a contributed recording into an editable narrative.
- Find photos from user-provided captions and visual descriptions.
- Offer tentative ordering while preserving uncertain dates.
Key features
Inside the platform
Keep the story attached to the photograph.
Original mobile interface concepts with fictional content. AI responses illustrate proposed interactions; they are not live model results.
Proposed technology stack
Proposed iOS architecture using Swift and SwiftUI. AI processing, storage and synchronization are design proposals for this concept, not integrations implemented by this portfolio.
- Swift
- SwiftUI
- Core Data
- 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 memory capture, inspect the proposed story conversation 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.