I Got Tired of Bookmarking Prayers, So I Built an App Instead

I pray the Rosary daily, sometimes more than once a day. For a long time my setup was embarrassingly low-tech for someone who builds apps for a living: open the phone browser, search for the prayers, bookmark them, and reopen the same tabs every time. It worked, but there was always a little bit of friction, and it stacked up.

The idea eventually clicked: what if I just had one app I could rely on instead of juggling browser tabs? I’d looked at a few of the existing apps in this space, and honestly, the UX in most of them didn’t sit right with me. So I decided to build my own.

That app is Angelus, and it’s now live on the App Store: Angelus - Catholic Prayer App

What it does

Angelus walks you through the Rosary bead by bead, no physical rosary required. It counts each Hail Mary with you so you always know exactly where you are in a decade, and it automatically highlights the day’s mystery so you’re not stopping mid-prayer to check. There’s also a full prayer and saints library underneath it, searchable, filterable, and available in English, Latin, and Tagalog.

No accounts, no data collection. Just a simple, focused tool.

Built with Flutter, guided by AI

This is the part I’m most excited to write about. I built Angelus in a matter of days, from idea to a released iOS app, with Claude Code doing a huge amount of the development legwork.

This was my first time building a personal production app leaning this heavily on AI, and I went in curious rather than confident. I came out pleasantly surprised at how smooth it was.

I think a lot of that came down to the fact that I already know how to build apps. I wasn’t discovering what I wanted as I went; I knew the UX I was after, I knew the architecture I wanted, and I knew what “done” looked like for a v1. That made prompting and guiding the AI feel almost second nature, more like directing a very fast, very capable collaborator than wrestling with a black box. What used to be days of scaffolding and boilerplate turned into a conversation where I could describe the behavior I wanted and iterate on it in real time.

I’m not going to pretend this is a “no-code, no-skill” story. It isn’t. But if you already know what you want and how it should work, AI-assisted development compresses the distance between that idea and a working app dramatically. That gap, for me, used to be measured in weeks. This time it was days.

Where it stands now

The iOS app is live on the App Store and already at v1.1.0. The Android version is currently in closed testing, and I’ll need a few more volunteer testers before I can push it to production. If you’re on Android and wouldn’t mind helping test, reach out, I’d genuinely appreciate it.

This is very much a living project. I plan to keep maintaining and improving Angelus with iterative releases rather than treating v1 as a finish line.

If you’d like to try it, or you pray the Rosary and have thoughts on what would make this more useful day to day, I’d love to hear from you.