Apple introduces new AI integration APIs and expanded agentic coding tools in Xcode 27
Apple introduced new intelligence capabilities, expanded productivity features in Xcode 27, and platform improvements. Key updates include new AI integration APIs via Foundation Models and Core AI, agentic coding tools with support for models from Anthropic, Google, and OpenAI, and design improvements like Liquid Glass. Developer betas for iOS 27, iPadOS 27, macOS 27, watchOS 27, tvOS 27, visionOS 27, and Xcode 27 are available today.

*this image is generated using AI for illustrative purposes only.
Apple today introduced new intelligence capabilities, expanded productivity features in Xcode, and platform improvements that make apps faster, more adaptive, and easier to build. The latest enhancements to Apple Intelligence and the introduction of Siri AI enable developers to make their apps' content and capabilities more discoverable and accessible across the system. Updates to the App Intents framework allow developers to connect their apps to Siri AI capabilities, including personal context understanding, app actions, and onscreen awareness.
Intelligence Frameworks and Core AI
New intelligence frameworks allow developers to build AI features into their apps more easily, tapping into powerful models from Apple and others. The Foundation Models framework now serves as a single native Swift API that supports more powerful on-device models with image input, support for server models, and the ability to build custom skills. Developers can tap into the next generation of Apple Foundation Models, custom-built in collaboration with Google and its Gemini models. To ensure accessibility, developers enrolled in the App Store Small Business Program with fewer than 2 million total first-time App Store downloads can access the next generation of Apple Foundation Models running on Private Cloud Compute at no cloud API cost. Developers can also leverage models of their choice, like Claude and Gemini, or those from any other provider that implements the new language model protocol. The framework introduces Dynamic Profiles, enabling developers to update how models interact with their apps on the fly.
For developers who want to bring their own custom models into their app, Core AI is a brand-new framework designed to run models on device. Core AI provides an architecture optimized for the unified memory and Neural Engine of Apple silicon, allowing developers to deploy full-scale LLMs locally.
Xcode 27 and Agentic Coding
Xcode 27 takes the next big step in agentic coding, bringing the full power of today's best models and agents from Anthropic, Google, and OpenAI directly into a developer's workflow. Conversations with coding agents feature interactive planning, multiturn Q&A, and a canvas that can render Markdown and display code changes and previews. Xcode 27 gives coding agents the tools to validate their own work, allowing them to run autonomously for longer, such as writing and running tests, trying ideas in isolation with Playgrounds, checking visual changes with previews, and interacting with the simulator in the new Device Hub. With plug-ins, developers can extend Xcode with custom skills, bring in tools through the Model Context Protocol, and connect any agent compatible with the Agent Client Protocol. GitHub and Figma are the first to offer seamless installation between their tools and Xcode.
In addition to coding intelligence, Xcode 27 delivers improvements across the board. The application is now Apple silicon only, 30 percent smaller, and delivers faster performance and a simpler setup process. It is also more personalizable, with a fully customizable toolbar and a new theme system. Xcode Cloud is now up to 2x faster, with new support for apps that use Metal and for visionOS builds.
Design, UI, and Gaming Tools
Liquid Glass provides a unified visual design that makes apps more expressive and instantly familiar across Apple platforms, with improvements to legibility, customizability, and consistency. A new transparency slider in Settings allows users to personalize their visual experience. SwiftUI makes apps more responsive without requiring developers to change their code through more efficient state initialization and faster layout rendering. The new Spatial Preview framework allows 3D models from Mac apps to be viewed spatially when streamed to Apple Vision Pro.
For game and spatial developers, new tools include Managed Background Assets to reduce game install sizes through intelligent, localized delivery, and a Steam Asset Converter to adapt PC games for Apple platforms. Game Porting Toolkit 4 accelerates Mac game development with open source skills for agents. Official Unity plug-ins bring native Apple integration for StoreKit and Background Assets. Reality Composer Pro 3 allows developers to build complete spatial experiences with new Live Previews combined with Mac Virtual Display.
Availability
Developer betas for iOS 27, iPadOS 27, macOS 27, watchOS 27, tvOS 27, visionOS 27, and Xcode 27 are available starting today. Apple Intelligence features are available only in supported regions.
How will the integration of Google Gemini models impact Apple's competitive positioning against other AI giants?
What are the potential privacy implications of allowing developers to run autonomous coding agents within Xcode?
Will the free cloud API access for small business developers significantly disrupt the AI app development market?


























