Cura

Context

I built Cura with the same setup as most of our apps at 14x: Claude Code, Xcode, Swift, on-device ML, RevenueCat. Same thesis as Signature Maker: proven market, competitors making money, but every existing app in the category looked outdated and ugly. I wanted to build a premium version.

I also had the pain point myself. Thousands of photos on my phone I never got around to sorting.

The problem

Camera rolls grow endlessly. Duplicates from burst mode, blurry shots you forgot to delete, screenshots from 3 years ago, old memes. Storage fills up, and no one has time to scroll through 10,000 photos manually deciding what stays and what goes.

The apps that solve this already exist, but they all feel like utility software from 2018. Cluttered UIs, slow scanning, confusing flows. None of them felt like something you'd actually enjoy using.

The solution

A "Tinder for your camera roll" experience. AI scans your library on-device, finds the junk (duplicates, blurry shots, screenshots, similar photos), and presents them in a swipe interface. Left to delete, right to keep. Half a second per photo.

Key features:

• On-device ML for duplicate detection and blur scoring
• Similar photo grouping with side-by-side comparison
• Video compression (up to 80% reduction)
• Photo compression via HEIC conversion
• Bulk deletion with one tap
• 100% on-device, no cloud, no account

The hardest technical challenge was handling large photo libraries without creating hangups. Scanning thousands of photos with ML models while keeping the UI smooth required careful caching, background processing, and memory management. The state management around the swipe flow was also tricky: what happens when a user swipes 200 photos, closes the app, reopens it, and those photos haven't been batch-deleted yet? Getting that persistence layer right took real thought.

The duplicate detection and blur scoring worked astonishingly well though. On-device ML surprised me with how accurate it was, even on large libraries.

Outcomes

Revenue-wise, Cura only generated about €10 in sales. ASO alone didn't move the needle here, unlike Signature Maker which grew organically from day one.

The difference is clear in hindsight: signing a PDF is an urgent, immediate pain point. People search for it actively in the App Store when they need it. Cleaning your photo library is a "nice to have" that people procrastinate on forever. The intent behind the search is fundamentally weaker.

Retrospective

Not much I'd change about the product itself. The design is clean, the ML works great, the UX is satisfying. But it proved something important: when you're not solving an absolute, hair-on-fire pain point, you need marketing to drive awareness. The App Store won't do it for you.

Signature Maker works on pure ASO because people are actively searching for it right now, with urgency. Cura is the kind of app people think "I should do that someday" about. That "someday" intent doesn't translate to organic downloads.

Learnings

"Nice to have" apps need marketing. If your app solves a problem people procrastinate on, ASO alone won't work. You need content, ads, or some external push to remind people the problem exists. Compare that to pain-point apps where the user is already in the store, searching urgently.

On-device ML is production-ready. Core ML handled thousands of photos with solid accuracy for both duplicate detection and blur scoring. The bottleneck wasn't the ML, it was the surrounding infrastructure: caching, memory, state management, UI smoothness during heavy processing.