The Firebase team has been working on bringing Gemini to Apple's Foundation Models (AFM) framework, enabling seamless integration between local Apple silicon and server-side Gemini intelligence. I was on the ground at WWDC 26 to talk about this at the AiOS meet-up and record a special video walkthrough showing exactly how it works under the hood. Watch the WWDC special edition video walkthrough: https://www.youtube.com/watch?v=qx5QWrKhxM8
I've open-sourced Stratos, a suite of AI agent skills designed to teach your AI coding assistant (like Claude, Gemini, or Cursor) how to build beautiful, high-end Swift and SwiftUI APIs following the principles of Progressive Disclosure. npx skills add peterfriese/Stratos
Apple's official guidelines in Xcode 27 discourage using computed properties to split large SwiftUI views. Instead, developers should extract separate View structs with narrow, stable inputs to establish independent invalidation boundaries, which prevents unrelated state changes from triggering expensive parent view re-evaluations.
Designing custom view APIs to match Apple's native primitives keeps the learning curve minimal and ensures integration is seamless. By modeling semantics first, managing data flow with explicit Bindings or local State, and using custom view styles or Environment modifiers for customization, developer-friendly reusable components can be easily built and maintained.
DynamicProfiles are one of the Foundation Models framework’s hidden superpowers - they essentially form the basis for implementing agentic experiences. Artem explains how they work by way of implementing an “Economy switch” that can help your app safe tokens (and money).