Since iOS 18, I have an OpenIntent to open documents. For Siri AI, I understood that I need to annotate the entity with @AppIntent(schema: .system.open) for Siri AI to be able to open documents. This is only supported starting with iOS 27. I tried duplicating the intent (one for iOS 27, one for the other versions), however, Xcode complains and says that only one OpenIntent is possible per target entity. How are we supposed to: support Siri AI "open" functionality preserve functionality for older iOS versions ? Thank you

I'm trying to understand the intended relationship between OpenIntent and the new .system.open App Intent schema introduced in iOS 27. From the documentation: OpenIntent (available since iOS 16) is described as an intent that opens an associated item. iOS 27 introduces the .system.open schema, which also appears to represent opening an entity or piece of app content. My questions are: For an app that supports iOS 27+, is .system.open intended to replace OpenIntent, or do the two serve different purposes? For apps that support both iOS 26 and iOS 27+, is the recommended approach to have two structs that implement the same opening logic, one with @AppIntent(schema: .system.open) and the other implementing the OpenIntent protocol? Thanks! References: open protocol OpenIntent

I am using an iPhone 16 Pro with iOS 27 Public Beta. In the Netherlands, the Apple Intelligence option has disappeared from the settings.

I am getting FoundationModels.LanguageModelError error -1 when trying to use Foundation Models on the visionOS 27 simulator. It works on the iOS 27 simulator. Is this a bug with the visionOS 27 simulator specifically?

I would like to raise a platform-level question about the future relationship between Apple Intelligence, App Intents, iOS permissions, and third-party AI systems. I have been deeply invested in the Apple ecosystem for many years. One of Apple's greatest strengths is that iPhone, iPad, and Mac work together with very little friction. The other major strength is Apple's strong privacy and security model. Generative AI is now creating a new tension between those two strengths. On the Mac, users can explicitly grant AI tools relatively broad access to files, folders, and, in some cases, application controls. This has changed what non-technical users can accomplish. I am not a software developer, but with AI assistance I can now design workflows, create automation, work with structured data, and build tools on my Mac that would previously have required professional knowledge. In other words, AI has not merely made the Mac more efficient. It has expanded the capabilities of the user. This makes the restrictions on iPhone increasingly noticeable. The issue is not the computing power of the iPhone. Modern iPhones are extremely capable devices. The issue is that third-party AI systems cannot yet work with the user's personal context, application data, and device capabilities with the same degree of flexibility, even when the user explicitly wants to grant such access. My question is: Could iOS evolve toward a more general, user-controlled permission architecture for third-party AI agents? I am not suggesting unrestricted access to the device. I am suggesting a system in which users can explicitly grant narrow and persistent permissions to an AI provider or AI agent. For example: Allow read-only access to a specific folder. Allow search access to selected Notes or note categories. Allow access only to a particular Photos album. Allow calendar read access but not modification. Allow an AI to search Photos but never delete them. Allow routine read/search operations automatically, while requiring confirmation before modification, deletion, sending, purchasing, financial activity, or other sensitive actions. From a platform-design perspective, this could potentially be implemented as multiple layers: iOS defines the maximum permitted scope. The user explicitly chooses the resources and capabilities available to the AI. The AI provider is expected to operate within the minimum necessary scope. Sensitive or destructive actions require an additional confirmation boundary. Access can be reviewed, reduced, or revoked centrally by the user. This seems consistent with Apple's existing security philosophy rather than opposed to it. The goal would not be to give an AI "full access." The goal would be to create an OS-level capability model in which the user can safely delegate specific access and actions to AI. App Intents already provides a structured way for applications to expose actions and entities to the system. Apple Intelligence is also increasingly able to work with application capabilities and user context. The question is whether this model could eventually be extended into a broader framework for third-party AI systems. For example, rather than allowing ChatGPT, Claude, Gemini, or another model to directly inspect the device, iOS could remain the trusted intermediary. The AI could request a capability or a piece of context. iOS could evaluate: Which data is being requested? Has the user authorized this category? Is the request read-only or destructive? Does the request require confirmation? How much context should be disclosed? Should the AI receive raw data, structured data, or a filtered result? This would allow Apple to remain the security and permission authority while still letting users benefit from advanced external AI models. I believe this distinction is important. Apple does not necessarily need to expose raw device access to third-party models. Instead, Apple could expose a secure capability layer controlled by the OS and the user. This also raises a broader architectural question about Siri and Apple Intelligence. Does Siri itself need to become the most capable general-purpose AI model? Perhaps not. A possible architecture would be: Siri / Apple Intelligence understands user intent, manages personal context, controls permissions, identifies the appropriate application or data source, performs local or private operations where appropriate, and delegates advanced reasoning when needed. Third-party AI models provide advanced reasoning, planning, interpretation, generation, or domain-specific intelligence. iOS remains the trusted security boundary between the AI model and the user's personal environment. In such a system, Apple would not need to sacrifice privacy in order to support highly capable AI. It could instead become the platform that provides the safest interface between powerful AI systems and a user's personal digital environment. From a user-experience perspective, I believe this is becoming increasingly important. AI has made my Mac substantially more useful because it allows me to accomplish tasks that were previously beyond my technical ability. I would like that same expansion of capability on the iPhone. Today, the Apple ecosystem is seamless at the data and device level, but less seamless at the AI capability level. Mac can increasingly function as an AI-enabled working environment, while iPhone remains much more restricted. That difference may become more significant as AI agents become more capable. So my main request is: Please consider allowing iPhone users to grant third-party AI systems broader but carefully scoped access to device data and application capabilities. Not unrestricted access. Not a bypass around Apple's privacy model. Rather: user-controlled, granular, revocable, OS-mediated AI permissions. If Apple can provide that securely, I believe it could significantly improve the usefulness of iPhone while preserving the privacy and security principles that make the Apple ecosystem distinctive. I would be very interested to know whether App Intents, Apple Intelligence, or another future framework is intended to evolve in this direction.

Filed as FB23652582. In Xcode 27 beta, this no longer compiles when the deployment target is below iOS 27: @available(iOS 18.0, *) @AppEntity(schema: .photos.asset) struct AssetEntity: IndexedEntity { ... } // error: 'asset' is only available in iOS 27.0 or newer The identical source compiles under Xcode 26. It looks like the @AppEntity(schema:) macro now resolves .photos.asset to a declaration annotated for iOS 27, whereas in Xcode 26 it resolved to the (now-deprecated) iOS 16 declaration. What seems off: the .photos.album entity in the same domain still builds fine at an iOS 18 deployment target — only .asset requires iOS 27. That asymmetry is what makes me think it may be an unintended availability change rather than a deliberate one. Has anyone else hit this? And is this intended — i.e. is .photos.asset now meant to be iOS 27+ only, or should it still be usable from apps that deploy to iOS 18?

Regarding the 'weight list' of Siri: can you all provide technical specifics on how a model qualifies for this list, and can a developer-supplied model/adapter ever handle requests that originate from the system-wide Siri interface?

I am trying to build the example on device model example in video WWDC26/241 (What’s new in the Foundation Models framework). I have included the coreai-models package from GitHub but the build still fails with; What’s new in the Foundation Models framework Suggestions appreciated!

Hello, I'm a EU-based developer. Our app is distributed worldwide. I'd like to clarify the following regarding Siri AI and EU: is Siri AI unavailable to users based in EU, or to apps based in EU. In other words, will my app developed in Europe work with Siri AI for US users? Or the fact that my app is developed in Europe excludes it from compatibility with Siri AI? Kind regards, Bruno

My intents and entities show up in Shortcuts, and my tests that use App Intents Framework pass. But I can't for the life of me figure out why Siri won't work. I'm trying phrases like "Add to my list in ". All I ever get from Siri is variations of "I can't add items directly to " or "I can't add items to your lists in ". Does anyone see any issues with the following? ( I've left out some of the AppEnum and Entity types for brevity, but these are the main ones) @AppIntent(schema: .reminders.createReminder) struct AddToListIntent { var title: String var list: ListEntity? var note: AttributedString? var isFlagged: Bool? var images: [IntentFile] var tags: Set<String> var urls: [URL] var dueDate: DateComponents? var recurrence: Calendar.RecurrenceRule? var locationTrigger: LocationTriggerEntity? var section: SectionEntity? func perform() async throws -> some ReturnsValue<ReminderEntity> { let newReminder = ReminderEntity(id: "foo", reminder: .init(name: title)) return .result(value: newReminder) } } struct Reminder { var name: String } @AppEntity(schema: .reminders.reminder) struct ReminderEntity { // MARK: Static static let defaultQuery = ReminderEntityQuery() // MARK: Properties let id: String let reminder: Reminder @ComputedProperty(title: "Title") var title: String { reminder.name } var note: AttributedString? { nil } var tags: Set<String> { Set() } var urls: [URL] { [] } var dueDate: DateComponents? { nil } var recurrence: Calendar.RecurrenceRule? { nil } var isCompleted: Bool { false } var isFlagged: Bool? { nil } var creationDate: Date? { nil } var completionDate: Date? { nil } var list: ListEntity var locationTrigger: LocationTriggerEntity? { nil } var displayRepresentation: DisplayRepresentation { .init(title: "\(title)") } // MARK: Query struct ReminderEntityQuery: EntityQuery, EnumerableEntityQuery { func entities(for identifiers: [ReminderEntity.ID]) async throws -> [ReminderEntity] { identifiers.map { .init(id: $0, reminder: .init(name: "Foo")) } } func allEntities() async throws -> [ReminderEntity] { ["foo", "bar", "baz"].map { ReminderEntity(id: $0, reminder: .init(name: $0)) } } } } @AppEntity(schema: .reminders.list) struct ListEntity: AppEntity, IndexedEntity { let id: String let myName: String var name: String { myName } // 3. Define how this entity is displayed to the user in shortcuts/Siri var displayRepresentation: DisplayRepresentation { DisplayRepresentation(title: "\(myName)") } @Property var type: MyListType // 4. Provide a query so the system can resolve specific lists static var defaultQuery = ListEntityQuery() }

I am developing a third-party macOS application that uses Apple Foundation Models, including Private Cloud Compute (PCC). I would like to confirm the supported distribution requirements for this use case. Specifically: Can a third-party macOS application use Apple Foundation Models / PCC as part of its application functionality? Is PCC usage supported when the macOS application is distributed outside the Mac App Store using Developer ID signing and Apple notarization? Are there any additional entitlements, distribution requirements, or restrictions for PCC when distributing outside the Mac App Store? I intend to use only Apple's documented and supported APIs and will not attempt to bypass PCC availability, quota, entitlement, or other platform restrictions. Thank you.

We found an apparent iOS 27 WorkflowKit bug when implementing: @AppIntent(schema: .photos.editAsset) with an entity conforming to: @AppEntity(schema: .photos.asset) Despite Apple’s general guidance that schema entity types may be renamed, Siri only worked when our entity’s Swift type was named exactly AssetEntity. Controlled on-device results: AssetEntity — works PhotoAssetEntity — fails FooAssetEntity — fails For the failing names, neither the entity query nor perform() was reached. WorkflowKit logged: Failed to retrieve entity metadata Error Domain=WFActionErrorDomain Code=6 Siri responded: Unable to retrieve the data information to process. The generated App Intents metadata was internally consistent, and the issue persisted across clean installs and a device restart. Current workaround: name the .photos.asset entity type exactly AssetEntity. Tested with Xcode 27.0 beta (27A5252f) and iPadOS 27.0 (24A5423a). Filed with Apple as FB24604095 for anyone from Apple investigating this behavior.

I’m building Summon (https://github.com/NakliTechie/summon), an open-source native macOS launcher that uses the on-device SystemLanguageModel. Summon creates a fresh LanguageModelSession for each query and attaches only the read-only tools relevant to that query. It currently calls prewarm() after the first keystroke using a temporary session, then creates a different session for generation. The documentation describes prewarm(promptPrefix:) as loading the resources required “for this session.” I would value guidance on four points: Is the prewarming benefit scoped to that exact LanguageModelSession instance? Does a later session using the same SystemLanguageModel receive any benefit? For an ephemeral launcher, is retaining one session preferable to creating a fresh session per query? Which Foundation Models Instrument signal identifies an ineffective prewarm or cache invalidation? Thank You Chirag

I’m trying to understand the intended relationship between IndexedEntity.attributeSet, defaultAttributeSet, and displayRepresentation. For example: struct TrailEntity: IndexedEntity { var displayRepresentation: DisplayRepresentation { DisplayRepresentation( title: "(trail.name)", subtitle: "(trail.location)" ) } var attributeSet: CSSearchableItemAttributeSet { let attributes = CSSearchableItemAttributeSet() attributes.keywords = trail.keywords return attributes } } Should attributeSet instead be initialized with defaultAttributeSet and then have the additional attributes assigned to it? var attributeSet: CSSearchableItemAttributeSet { let attributes = defaultAttributeSet attributes.keywords = trail.keywords return attributes } The documentation says defaultAttributeSet contains values derived from displayRepresentation, but it also describes precedence between displayRepresentation and attributeSet, which suggests Spotlight reads them separately during indexing. So what is the intended pattern? Does overriding attributeSet require including defaultAttributeSet to preserve title/subtitle/image metadata, or is attributeSet only meant for additional Core Spotlight metadata? If the latter, what is the intended use case for overriding or directly using defaultAttributeSet?

皆さん、はじめまして。プログラミングに対する知識がないので、AIを使いながらiPadでTelloのドローンを操縦できるアプリを作っています。このアプリはシミュレーション飛行とドローンの実機飛行ができるアプリにしたいのですが、ドローンの実機飛行を行うためのWi‐Fi接続ができません。（iPadでのシミュレーション飛行が可能です）iPadの基本的な設定はAppleに教えていただき、設定変更を行いましたが、どうしても接続できないので、わかる方法を教えていただけると嬉しいです。 コードを添付いたしますので、ご教示ください。 ドローンアプリコード

I am developing a macOS developer tool that uses Apple Foundation Models, including the Private Cloud Compute (PCC) model. On macOS 27, the Foundation Models CLI provides fm serve, which exposes a local Chat Completions API, including: POST /v1/chat/completions My application communicates with this local API on the user's own Mac to provide agent-style development features. The Foundation Models CLI Legal Notice states: “You are also agreeing to not programmatically access or use Apple models through Apple software or services except as expressly permitted.” I would like to confirm whether using the local API intentionally exposed by fm serve from a third-party macOS application distributed to users is considered an expressly permitted use. The application would: use only the interfaces and endpoints officially exposed by the fm CLI; run fm serve locally on the user's Mac; use the user's own Foundation Models / PCC availability and quota; not bypass quota limits; not use private or undocumented APIs; not reverse engineer Apple services. Is this use of fm serve permitted for a distributed third-party macOS application? If so, are there any additional requirements or restrictions that developers should follow when distributing an application that integrates with fm serve in this way? Thank you.

I would like to understand the foundations of connecting my apps api structure to corporate reporting in regards to textile manufacturing. utilizing the core ML and vision through smartphone to link raw data capture and strategic execution.

I'm looking for a supported way to read intermediate tensors from a model executing on the Apple Neural Engine - specifically the output of an individual node in the compiled graph, rather than only the final output. What I'm trying to do: validate a from-weights reimplementation of a model against the real thing, layer by layer. Comparing only the final output tells me the reimplementation is wrong but not where; a per-layer comparison would localise it immediately. What I've established so far: A compiled ANE program can be executed unprivileged through the public graph API, and the final readout matches, so the execution path itself is reachable. Intermediate activations don't appear in host memory during normal operation, which is expected since the scheduler keeps them in accelerator-local storage. Requesting a per-node output appears to hit a kernel-side check that an ordinary process doesn't satisfy. Questions: Is there a supported API for retrieving per-node outputs from an ANE-scheduled graph - a debug or instrumentation mode, an Instruments template, or a Core ML compute-plan facility that surfaces them? Failing that, is there a supported way to make a specific node materialise its output to a host-visible buffer - for example by splitting the graph, marking an intermediate tensor as a model output, or compiling with that node as a terminal operation? I'm aware this may change scheduling and defeat the purpose, but I'd like to know whether it's the intended approach. If neither exists, is that a deliberate design boundary rather than a gap? A clear "no" is a useful answer and I'll stop looking. I'm not asking about any particular shipped model, and this isn't a request to bypass anything - the question is whether the platform exposes per-node observability for ANE execution at all, and if so what the supported entry point is. Thanks.

I’m evaluating a third-party Swift-based “orchestration layer” for enterprise AI workloads on Apple Silicon — it claims to handle job queuing, scheduling, batching, memory management, monitoring, auditing, and failover on top of on-device inference. Given the Core AI framework’s device-specialization step and InferenceFunction pipeline (and MLX’s unified-memory model), how much of this kind of orchestration is already handled natively versus something a developer would still need to build themselves? Specifically: 1. Does Core AI’s inference pipeline provide any built-in job queuing/batching across multiple concurrent requests, or is that entirely app-side? 2. Is there native failover/monitoring tooling for on-device inference, or would a developer need to build that themselves (e.g., via os_log, MetricKit, custom retry logic)? 3. For memory management across CPU/GPU/ANE, does unified memory in MLX/Core AI eliminate most of the manual management a custom orchestration layer would otherwise need to solve? Trying to understand what’s genuinely differentiated in a third-party layer versus what Apple’s stack already provides out of the box. Appreciate any insight from folks who’ve built with Core AI/MLX in production.

import Playgrounds import FoundationModels #Playground { do { let session = LanguageModelSession() let response = try await session.respond( to: "Explain SwiftUI in one sentence." ) print(response.content) } catch { print("Error: \(error)") } }``` I tested Foundation Models with this simple code, and it generated this error: "Error Domain=ModelManagerServices.ModelManagerError Code=1026 \"(null)\" UserInfo={NSMultipleUnderlyingErrorsKey=(\n)}" I tried restarting my Mac and Apple Intelligence, but that didn't work. What did work was updating Xcode and the simulators to the latest possible version.