We spent 2 weeks implementing the New Architecture and trying to understand its benefits and limits. That included asking friends at Instagram, Spotify, and other teams what they thought.

It wasn't even close to being ready. And worse: unreliable. We pivoted and spent the winter in "deep work" mode learning Swift..

That moment was a "bet the farm" kind of moment. We knew that AI struggled hard with Swift/SwiftUI and understanding the layout of the applications.

Worse, there are no crypto packages to lean on like viem or @peterferguson.eth's react-native-passkeys.

So we just wrote everything ourselves using Swift Crypto. And got way better at prompting.

Predictions Protocol https://onit.fun | react-native-passkeys maintainer | Variant Founder Fellow | Cambridge Alum | Formerly Ireland's #3 powerlifter (74kg)

That moment was a "bet the farm" kind of moment. We knew that AI struggled hard with Swift/SwiftUI and understanding the layout of the applications.

Worse, there are no crypto packages to lean on like viem or @peterferguson.eth's react-native-passkeys.

So we just wrote everything ourselves using Swift Crypto. And got way better at prompting.

https://github.com/apple/swift-crypto

We're now on the other side of the learning and refining. Every day is a compounding day. I figure we're about a month out from the App Store. 

Then about a few months out from data science worth bragging about.

Would love to CTO, but will need funds/grants from EF to cover the roadmap and maintainer workload. Otherwise we have a patchy library that only covers specific use cases.

will you spin out / OS the swift library?

Have you tried Claude Code and shoving all your research and structure into a CLAUDE.md? I found this helped dramatically. Or cursor rules. Spend a lot on context but its WAY better than vanilla

January to about mid-April we did it mostly without AI, mid-April to now, AI is doing most of the structured thinking, but still gotta implement it by hand. There's quite a bit of hallucination and false confidence/sidequesting it will perform.

With crypto libraries you can't go too far off the directive.

Do you think this would have been tractable with your team size and experience without AI assistance?