Apple Intelligence

The Foundation Models framework is a native Swift API that gives you direct access to Apple Foundation Models — on device and in Private Cloud Compute* — as well as any model provider with a Swift package conforming to the Language Model protocol.

From there, multimodal prompts and on-device Vision framework tools let your app reason about images alongside text, while Dynamic Profiles let you swap models, tools, and instructions within a continuous session so your app's intelligence can adapt in real time. Then use the Evaluations framework to ensure your AI features work reliably across dynamic conditions.

The App Intents framework connects your app to Apple Intelligence and Siri AI through schemas — recognizable structures built on years of language model training — that make your app's content discoverable and its capabilities available through natural language with less code.

Entity schemas contribute your content to the Spotlight semantic index for personal context understanding, while intent schemas let people take action on that content naturally, with no specific phrases to define and no code changes needed as Siri's language understanding evolves. The View Annotations API extends this further with on-screen awareness, letting you map views to entities so people can reference and act on what's in front of them conversationally.

Image Playground lets people generate high-quality images in virtually any style — including photorealistic — transform their own photos using natural language descriptions, and modify images using descriptions or with touch. Images are generated on Private Cloud Compute, so photos are never stored or shared. When you use the Image Playground API, you can support these new image creation capabilities right from your apps.

Shortcuts uses Apple Intelligence to assemble automations from natural language descriptions, so people can incorporate your app's capabilities into powerful multistep workflows simply by describing what they want to do. The Shortcuts app lets people automate tasks by connecting system and app actions. When you adopt App Intents, your app's actions and entities become part of that ecosystem — available alongside features like Use Model.

Visual Intelligence lets people search for information and take action on what's in front of them — through the Camera app on iPhone, onscreen content on Mac and iPad, and objects in the world on Apple Vision Pro. Integrating your app gives people a way to view your matching content in the moment and launch directly into your app for richer detail or additional results, surfacing your app naturally across more of the system.

You can write and edit with Siri systemwide, helping people compose, rewrite, proofread, and summarize text. If you're using any of the standard UI frameworks to render text fields, your app will automatically have this ability. Or if your app has custom text controls you can adopt APIs to integrate this into your app.

Enhance your app to let people make the perfect emoji to express themselves in the moment while using your app. Genmoji is automatically supported as stickers in your app when you use system text controls, and there are APIs for you to render them with custom text engines.