A new Apple framework for measuring the quality and reliability of intelligent features powered by generative AI. It integrates with Swift Testing to let developers define datasets, metrics, and optimization targets that automatically assess probabilistic outputs from language models.
ā¢ Solves the core testing problem with generative AI: since the same input can produce different outputs, traditional unit tests are insufficient ā Evaluations lets you measure how often your feature behaves correctly across many samples
ā¢ Integrates directly with Swift Testing via the .evaluates trait and #expect macros, so evaluations run alongside your existing test suite in Xcode's test report
ā¢ Includes a SampleGenerator for synthetically expanding small datasets into thousands of samples, enabling statistically meaningful trend detection without manual data authoring
Foundation Models is a new Apple framework introduced in iOS 27 that gives developers on-device access to the same Apple Intelligence language model powering system features, enabling text generation, structured output, and tool-calling entirely on-device without a network connection.
Visual Intelligence brings iOS 17's Visual Look Up capabilities to a new developer-facing API surface in iOS 27, letting apps pipe live camera frames or static images through on-device scene understanding to extract subjects, text, barcodes, and rich semantic labels without any cloud round-trip.
iOS 27 opens the Foundation Models framework to third-party LLM providers via a new public LanguageModel protocol, enabling anyone to integrate custom, server-based, or open-source models using the same Swift API as Apple's on-device system model.
In-depth guide
iOS 27 On-Device AI & Apple Intelligence āApp Schemas let developers describe their app's content and actions using pre-defined domain schemas (like the Calendar domain) so Siri can understand, search, and act on app data without custom NLP. Entities conforming to IndexedEntity are donated to Spotlight's semantic index, enabling natural-language queries over app content.