Overview
Readquill explores reading companion through a mobile experience built around an excerpt-first reading view with a collapsible discussion sheet. A reading companion for source-grounded discussion, personal annotation search and generated recall practice. The proposed journey connects passage capture, discuss passage, recall cards, reading trail. Four original phone showcases establish the visual direction, while the case study defines the supporting feature set and a proposed Kotlin architecture.



Original mobile interface concepts with fictional content. AI responses illustrate proposed interactions; they are not live model results.
Challenge
Readers need AI explanations grounded in passages they provide and a clear way to preserve their own interpretation. 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 passage capture and discuss passage connected within a short mobile flow.
- Make passage extraction correctable when the model misreads the input.
- Explain recall generation through visible references or user-selected preferences.
- Keep changes, sharing and data retention under explicit user control.
Solution
The design begins with an excerpt-first reading view with a collapsible discussion sheet, using large touch targets, short task sequences and contextual sheets. Turn a photographed user-provided excerpt into editable text. Explain selected passages with visible source anchors. The companion views keep drafts, original material and accepted decisions distinct. A cream, oxblood and charcoal visual system gives this app its own character within the collection.
- Turn a photographed user-provided excerpt into editable text.
- Explain selected passages with visible source anchors.
- Draft self-check questions from the chosen material.
- Find connections among the reader's own saved annotations.
Results
4
Original mobile
showcase views12
Designed
feature areas4
Proposed AI
workflows


