FocusShelf

What the company appears to be: FocusShelf (self-described as "Liuguang") is a native iOS application for personal cultural journaling around books, films, and music. It allows users to record, organize, and reflect on their engagement with these media types in a local-first environment.

What changed: The project was developed during the OpenAI Build Week hackathon using Codex as an engineering partner. It evolved from a broad idea into a working native iPhone app with metadata integration across multiple sources.

Single most important open question: Is there evidence of user adoption or engagement beyond the single developer's personal use?

The description states that this is a self-built project by one individual, with no evidence of revenue, customers, or traction. The author describes technical implementation and product features but does not provide any data on usage, retention, monetization, or market validation.

• The description states that Liuguang is a "local-first cultural journal for books, films, and music"
• Users can record what they want to read, watch, or hear; what they are currently experiencing; and what they have completed
• It supports searching multiple metadata sources without manual entry of titles, creators, covers, release dates, regions, or genres
• The app allows adding ratings, tags, progress, and personal reflections
• It distinguishes between different media types (albums, singles, songs, EPs, live recordings)
• Features include importing album track lists and lyrics with distraction-free performance mode
• Users receive daily recommendations that exclude works already saved in the library
• The app includes annual activity review through weighted keyword bubbles
• It supports exporting, importing, or erasing the local library
• Interface uses Apple's Liquid Glass system for visual design

Evidence strength: Self-reported and unverified. No independent verification of functionality or user experience.

• The description states that streaming services remember what users played, reading platforms remember what they bought, and movie databases remember what they rated—but none remember why a work mattered to the user
• The author positions this as a quiet, personal place for preserving cultural experiences that continue to glow after the experience ends
• The name "Liuguang" means "keeping the light," suggesting a focus on preserving meaningful cultural moments
• The project evolved from an idea about fragmented cultural memories to a working native iPhone application during OpenAI Build Week

Evidence strength: Self-reported positioning and intent. No evidence of market testing, user feedback, or competitive positioning validation.

• Not evidenced. The description does not identify specific customer segments, personas, or ideal customer profiles
• The author describes the product as personal and local-first but does not specify target demographics or use cases beyond individual cultural journaling
• No evidence of market research, user interviews, or competitive analysis to inform customer targeting

• Not evidenced. There is no mention of pricing models, monetization strategies, revenue streams, or business model assumptions in the description
• The author does not describe any commercial aspects beyond personal development and potential future features like iCloud synchronization or OpenAI reflection layers
• No evidence of customer acquisition costs, unit economics, or sales processes

• Built with Swift 6 using SwiftUI and SwiftData, targeting iOS 26
• Uses a provider-based metadata architecture that converts external results into shared MediaSnapshot model
• Connects to sources including Open Library, Apple Books, Google Books, Douban, IMDb, Rotten Tomatoes, Apple Music, Spotify, and LRCLIB
• Implements actor-based disk cache for cover artwork with URL hashing using CryptoKit
• Uses file protection and LRU-style storage limits to manage cache growth
• Recommendation engine is local and explainable, scoring candidates using media-type affinity, creators, tags, daily seeds, and recent recommendation history
• Implements Apple's Liquid Glass system with native SwiftUI APIs
• Core Motion integration for annual keyword bubbles responding to device tilt

Evidence strength: Self-reported technical implementation details. No evidence of production deployment, performance metrics, or scalability considerations.

• Not evidenced. The description provides no data on user engagement, retention, adoption rates, or market traction
• The project is described as a single-person development effort during a hackathon
• No evidence of revenue generation, customer base, or product-market fit validation
• No mention of user feedback loops, feature usage analytics, or iterative improvements beyond the initial build

• Not evidenced. The description does not identify direct or indirect competitors in the cultural journaling or personal media tracking space
• No evidence of competitive analysis, market sizing, or positioning relative to existing solutions
• The author mentions that streaming services, reading platforms, and movie databases remember user activity but do not remember why a work mattered—this is presented as a gap rather than competitive landscape analysis

• Single developer dependency: The project was built by one person with no evidence of team or organizational support
• Limited market validation: No evidence of user testing, feedback, or adoption beyond the author's personal use
• Technical complexity without scale evidence: The described technical architecture is complex but lacks evidence of production deployment or performance validation
• Unclear commercial viability: No business model, pricing, or monetization strategy described
• Hackathon origin: The project was developed during a hackathon, suggesting early-stage development with unknown maturity or long-term commitment

1. What specific user problems are you solving that existing solutions don't address?
2. How do you plan to validate market demand for this product beyond personal use?
3. What is your timeline and approach for building out the team and scaling the product?
4. How do you intend to monetize this product, and what pricing model are you considering?
5. What are the key technical challenges that remain unresolved in the current implementation?
6. How do you plan to handle data privacy and user control as features expand?
7. What is your strategy for growing user engagement and retention beyond initial adoption?