Two Apps, Fourteen Hours
Last week, Claude and I built two Android apps and published them to the Google Play Store. Total development time: 14 hours.
This is how it happened.
App 1: Vault
I wanted a secure, private vault on my Android device. Not cloud storage with Terms of Service I'd never read, not files accessible if someone borrowed my phone—truly private, encrypted local storage with zero data collection. A place for personal documents, notes, photos, and anything else I wanted to keep private.
- I can't trust any app that's not open source, and
- I need some way of knowing the app I'm running matches the source and hasn't been tampered with.
That level of verifiable trust is non-negotiable. We couldn't find anything like it. So we built one.
The Timeline
Hours 0–5: Core App to Play Store
Biometric auth, camera, encrypted storage—none of these are hard. Flutter has libraries for all of them. Scaffolding a project takes Claude about thirty seconds. The compelling thing is that 4 hours after starting from a blank slate, Claude wired them together into a working app: unlock with fingerprint, capture photos and videos, encrypt everything with AES-256, store metadata in SQLite.
The last hour shifted to Play Store preparation—app signing, adaptive icons, privacy policy, release build. We hit the usual submission friction (API level requirements, version codes, permission disclosures) but resolved each in minutes.
By hour 5, the app was submitted to Google Play.
Hours 5–8: Expanding Scope
After a day of using it, a vault that only stores camera photos felt limiting. We added:
- File import from device storage
- Encrypted markdown notes
- PDF viewing
This transformed it from "photo vault" to "general-purpose encrypted storage."
Hours 8–10: Polish
Real-world testing revealed UX issues: photo orientation was wrong on some images, the gallery needed filtering and grouping, thumbnails would improve navigation. Fixed each as they surfaced.
Total: ~10 hours to production.
What We Built
|
Security-First Architecture
- AES-256-CBC encryption for all files - Password + biometric authentication (fingerprint/face) - Auto-lock when app backgrounds or screen locks - Local-only storage (no cloud, no network) - Zero analytics, zero trackingContent & Features - Built-in camera for photos and videos - Import any file from device storage - Markdown editor for encrypted notes - PDF viewer - Photo viewer with pinch-to-zoom and video playback |
How We Built It
This was the first project where I wrote zero code.
I've been programming professionally for over 30 years. In every previous software project, I contributed code directly—regardless of title: VP of Engineering / CTO / Owner—sometimes to the chagrin of my developers. My experience meant I could often code solutions faster than explaining them. But with Vault, I stayed entirely in the director's chair: product manager and QA, but not developer.
Claude handled all implementation. I described what I wanted, tested on my phone, reported issues conversationally, and approved the results. The dynamic worked.
App 2: Gems
When I showed Vault to my wife, she had zero interest. Apparently secure file encryption doesn't spark joy.
When I was eight, my dad and I moved to a new town. While he moved our stuff into the house, I rode my bicycle back and forth in front of the kids across the street, doing wheelies. My wife plays match-3 games. Building Gems was the same impulse—showing off for someone whose opinion I cared about.
Here's the actual transcript of the project kick-off:
Me: "I'd like us to consider writing a game app... a game like Bejeweled. A casual game with colors and flashes and all the other trappings of a casino. Like the vault app, we'll make it open source, give it away for free, no ads. You up for helping me do that?"
Claude: "Okay, I've reviewed the vault_app. Here's what I'm seeing:
| What We Can Copy | Source | Notes |
|---|---|---|
| Project scaffold | Flutter setup, pubspec structure | New app ID, name |
| Android build.gradle | Signing config, SDK versions | Change package ID |
| main.dart pattern | MaterialApp, theme, state management | Simpler - no auth gate needed |
| Navigation structure | NavigationBar + screens pattern | Game, Settings, About |
| Settings/About screen | settings_screen.dart | Adapt for game settings |
| Icon generation | flutter_launcher_icons setup | New icon design |
...Want me to scaffold out the project? Sound good?"
Me: "heck yeah. That sounds great! Please proceed"
Hours 0–1.5: Core Game to Playable
Within 90 minutes, the game was functional.
What got built:
- Match-3 detection and cascade physics
- Four game modes (Timed, Moves, Target, Zen)
- Animated starfield background
- Pinch-to-zoom grid sizing (5x5 to 10x10)
- Leaderboards with arcade-style name entry
My role: Facilitate feature ideation conversations, approve features, QA.
Claude's role: Participate in ideation, write and deploy the code.
Hours 1.5–2.5: Store Preparation
README, screenshots, store listing, submission. The patterns from Vault made this fast.
Hours 2.5–4: Polish via Real-World QA
I handed my wife my phone: "Play this and tell me what's wrong."
Her feedback was specific:
"The swipe sensitivity is too low. I had to fall back to tapping." → Fixed in minutes.
"The screen shake animation and flashing is confusing and bad—I'm trying to plan my next move." → Implemented per-gem animation tracking. Only affected columns animate.
"There's no dopamine hit." → Built a complete combo celebration system with particles and multiplier badges.
Each fix took under five minutes. Test, report conversationally, get fix, repeat.
Total: ~4 hours to production.
The Lightswitch
Early in my career, I lived through one phase transition in how software gets built: the shift from waterfall to agile.
Development cycles collapsed from 2-3 years to 2-3 months. It didn't happen gradually. It happened like a lightswitch. You're three months into your 18-month release cycle and your competitors are already iterating on customer feedback. Companies that recognized it early had an advantage. Companies that didn't got left behind.
Another lightswitch moment has happened. Development cycles have collapsed again—from 2-3 months to 2-3 days.
Two production apps. Fourteen hours total. Both on the Google Play Store. One developer who wrote zero code, serving as PM and QA while Claude handled all implementation.
This isn't futurism. This isn't a prediction about where things are going. This is what happened last week. And just like the agile transition, most people haven't noticed yet.
The Only Thing That Matters
Yes, this article was written with Claude. Go ahead—call it AI slop.
But then play the game:
|
Core Game
- Match-3 with swap mechanics - Cascade physics (gravity, fill) - No-moves detection with auto-shuffle - Pinch-to-zoom grid (5x5 to 10x10)Game Modes - Timed: 90 seconds, maximize score - Moves: 30 moves, strategic play - Target: Progressive levels - Zen: Endless relaxationPolish - Animated starfield background - Combo celebrations with particles - Leaderboards with name entry - Per-gem animation tracking |
There's a tendency by some to dismiss AI-generated work reflexively. Hunting for emdashes as a proxy for quality. Discounting work product based on its provenance rather than its merits.
The only thing that matters is the quality of the work product. Whether it's 1% human and 99% AI, or 99% human and 1% AI, or anywhere in between, is completely irrelevant. Does the vault keep your files encrypted? Can you read the source code and verify what it does? Does the game feel good to play?
Everything else is distraction.
We built these apps in the open. The source code is public. We're giving Claude full credit for its contributions. Judge them on their merits.
Try Them
| App | Description | Install | Source |
|---|---|---|---|
| Vault | Encrypted local storage for documents, notes, photos, and files | Google Play | GitHub |
| Gems | A match-3 puzzle game with four game modes and no ads | Google Play | GitHub |
Contribute, if you'd like, with or without your AI collaborators.
What will you build?
Want This For Your Organization?
This is what we do. We help organizations adopt AI-assisted development and achieve the same kind of timeline compression.
Read about our methodology: Vibe Coding: A Human-AI Development Methodology
See our 11-year track record: Our Journey
Work with us: Contact to discuss how we can help your team build faster.