Hello Team, I am writing to seek clarification regarding an issue I am encountering while integrating App Intents within my application. I have configured an App Intent designed to accept an IntentFile as a parameter for processing. When testing this functionality via the Siri interface, I attach the image file and provide the trigger phrase as expected. However, Siri does not seem to recognize or associate the attached image as the required IntentFile. Consequently, the interaction fails to proceed, and Siri continues to prompt me to select a file. Could you please advise if there is a specific configuration requirement or a known limitation regarding how Siri handles file attachments for IntentFile parameters? I would appreciate any guidance on whether this is an issue with my current implementation or if I am missing a necessary step in the setup process. Thanks & Regards Suresh

I am trying to decide what technology to adopt for local AI inference on mobile devices. I tried the EdgeGallery demo app and was genuinely impressed. For an app using local Gemma 4, LiteRT-LM gives me a shared, OS-managed model on Android via AICore, up-to-date Gemma 4 support, and a working ANE/Core ML delegate on iOS today. What does building on Core AI’s .aimodel pipeline get me that LiteRT-LM doesn’t? Core AI has no cross-app shared memory, and every app has to bring its own model resources regardless. Also, the current model catalog seems to trail LiteRT’s. What am I missing?

Apologies, if I've missed the answer already here, I've searched around but can't find it. Foundation models and Private Cloud Compute require Apple Intelligence to be enabled in Settings as mentioned here. At the same time it says that Foundation Models PCC calls are supported on all Apple Watch models that run WatchOS 27. So, will there be a seperate Apple Intelligence setting in WatchOS 27 for those devices? Otherwise if a user has an Apple Watch Series 11 (which does support Apple Intelligence) paired with an iPhone 15 (which doesn't support Apple Intelligence), will they be unable to use the Foundation Models PCC calls from WatchOS in my app? Despite the fact the iPhone isn't involved in these queries anyway?

Hi guys, I am a new core developer. Recently I am trying the newly released core ai debugger tool and meet some issues. I am not sure whether the related functions of debugger is ready in beta package. Reference Run: aimodel on device versus intermediate dump I used the intermediate exporting api to export the intermediate dump data of MobileNet2.0 and converted the same MobileNet Model to .aimodel. But the compare button is not usable. the suffix of intermediate file suffix is OK(can be selected). The debugger is a GUI so I cannot figure out whether I exported the intermediate data incorrectly. (1st attached png ) on device model run compare I just simply tried the different computing unit and different input for a simple 'add/sub/mul/div' toy model. Especially set the input different but the comparison results seems to be empty I am not sure whether I modify the debugger tool incorrectly. Hope someone sharing experience. My Gratitude.

I've integrated my app with Visual Intelligence (iOS 26) using the semanticContentSearch schema. Image results are populated via an IntentValueQuery returning my entities, and the "More results" button is backed by an intent declared as: @available(iOS 26.0, *) @AppIntent(schema: .visualIntelligence.semanticContentSearch) struct ShowSearchResultsIntent { static let title: LocalizedStringResource = "Search products by image" static let openAppWhenRun: Bool = true var semanticContent: SemanticContentDescriptor func perform() async throws -> some IntentResult { /* deep-link into in-app search */ } } From WWDC25 (session 275) and WWDC26 (session 297) my understanding is that: the "More results" button is provided automatically by the system once this schema intent is adopted; returning an empty array from the value query lets the system show an empty response; my app appears as a result tab alongside other adopting apps, and the system decides the ordering based on the available image search providers on the device. I have a few questions about how much of this an app can control at runtime: "More results" button Is there any supported way to conditionally show or hide the system "More results" button at runtime (e.g., region, A/B test, server-driven feature flag)? Or is it strictly tied to the static presence of the semanticContentSearch intent? If IntentValueQuery returns an empty array, does the "More results" button still appear? Is there any API to suppress the button while keeping the schema intent declared? App result tab ordering How exactly does the system decide the order of the app result tabs? Is it based on relevance/similarity, app category, user behavior, or something else? Is there anything a developer can do to influence where their tab appears, or is ordering entirely system-controlled? App result tab presence / opt-out Once the integration is implemented, my app's tab appears automatically. Is there a supported way to conditionally opt out of appearing as a result tab at runtime (e.g., based on region or a feature flag)? Or is the only way to not appear to omit the integration at build time (or gate it by OS availability)? Thanks!

I'm developing an iOS app that uses imagePlaygroundSheet to generate images based on AI-generated prompts (not user-typed text). I would like to confirm whether the following usage is permitted under the Apple Developer Program License Agreement: Generate an image using imagePlaygroundSheet within my app Pass the resulting image (obtained via the completion handler URL) as an input to a third-party video generation API (e.g., to create an image-to-video animation) Offer this video generation as a paid feature (consumable in-app purchase) within my app I've reviewed Section 3.2(8) of the ADPLA, which prohibits using "output generated from an Apple model to train, fine-tune, or improve another artificial intelligence model." My understanding is that this clause is specifically about training/improving AI models, not about using the output image as a content input for a separate processing step (e.g., animation). Could someone confirm: Whether passing imagePlaygroundSheet output to a third-party API for further processing (not training) is permitted Whether monetizing a feature that uses this combined output is permitted Thank you in advance for any guidance.

I’m on a base iPhone 17 and I‘ve been approved from the waitlist over two weeks ago and when I use Siri, I get the old Siri from before Apple Intelligence was a thing (Glowy orb at the bottom). Inside Siri settings, it looks like it’s supposed to be set up for the new SirI as it shows the app settings. Here are my observations I have found from using beta 1 to 2. Beta 1: Whenever I have the new Siri “enabled”, there is no app I can type “siri://“ and it‘ll open the Siri open saying that’s there’s an update in progress. But if I type that in when I’m using the previous Siri, the app is there and it’s blank When new Siri is ”enabled” and whenever I ask Siri a question she’ll either think and never stop or output a blank answer. But when I turn Siri back to its previous version and open the “sir://“, it stores the conversation and when I open it, it actually answered my question. Beta 2: When installing beta 2 I said “new Siri“ enabled Once it was done installing, I went to iPhone storage and saw that “Apple Intelligence“ storage is increasing size. But then after a minute, it went back down to 14GB Still gave me the old Siri UI Now the siri app is not accessible when typing “siri://“ Siri mode is now in the camera app but it says it’s unavailable The ChatGPT extension area is now blocked because assets are downloading Whenever I visual intelligence and press ask it says that siri support is downloading I left siri alone for 3 days and nothing happened. Still stuck with old siri The ask siri option is everywhere now and when I press it, nothing happens Right now I’m using the previous version of Siri and hoping this bug will be patched and I can use the new Siri AI in Beta 3. *the screenshot provided shows what happens when I use Siri in beta 2 when it’s enabled.

If I attempt to use a LongRunningIntent from a SwiftUI Button, using the Button(_:AppIntent:) control, I get the following errors: [LongRunningIntent <<E:<unknown>>>] No IntentContext available performBackgroundTask threw: noContext Intent failed to execute with error: LNPerformActionErrorCodeUnsupportedValueType It runs as expected when run from the Shortcuts app, but fails when run from a button within the app. Feedback ID (with sample app): FB23492034

Currently, I have spotlight entities show up when I search for them using Spotlight on iOS 27. These entities are things that are important for users, like campus buildings, accessible entrances, assignments, and more. However, after getting access to Siri AI, it seems that none of this information at all is available to Siri, yet all of it is sitting there in the spotlight index and viewable with a written query. I was told by an Apple Engineer that creating Indexed and EnumerableEntities, and indexing them via the App Intents framework, should expose information about these items to Siri, so if I query: "[Building name] in Ohio State" it would at least show me what the app has for that information. Presently, Siri uses the web for everything and doesn't pull in any spotlight information for my app, despite either creating wrapper entities or using the API associating with spotlight. With Siri AI, it would be so much more helpful for a disabled user to say "Orton Hall accessible entrance" and Siri to know that there's 1 accessible entrance indexed in spotlight in my app, and then show or open it, instead of querying the web or saying it can't answer the question. It has all available information already in spotlight to answer this question. Currently, as far as I'm aware, something like this simply doesn't work, unless your app conforms to the strict use cases of making reminders or calendar events, all of which aren't useful here. Can a Frameworks engineer please clarify precisely when and how IndexedEntities (paired with an a corresponding macro-annotated OpenIntent) eg: @AppIntent(schema: .system.open) struct OpenBuildingIntent: OpenIntent { @Parameter(title: "Building") var Building: BuildingEntity ... will or will not be visible using Siri AI? To me it seems I have wasted a lot of time porting actions within my app to App Intents, and viewable entities with AppEntity, only to have Siri not be able to use any of this information out of the box.

Hi everyone, I've submitted a Feedback request (FB23469644) asking to introduce a generic Transportation Journey schema for App Intents. At the moment, there doesn't seem to be a way to donate structured public transportation trips (train, flight, bus, ferry, etc.) to Siri's semantic index. While many travel apps already have rich journey data, there is no common semantic model that represents: Multi-leg journeys Departure and arrival stations/airports/stops Platforms, tracks, gates, terminals Scheduled and real-time departure/arrival information Delays and cancellations Ticket and reservation information This seems like a natural addition to the existing App Intents schemas and would enable Siri, Spotlight, and Apple Intelligence to better understand upcoming journeys across all transportation providers. If you're building a travel or mobility app and have encountered the same limitation, I'd appreciate hearing your thoughts. Any idea if the old Siri event suggestion API gets is indexed by Siri Semantic Index / Siri AI?

Hello, I’m implementing the AppIntents framework in my app. I want to translate the TypeDisplayRepresentation that is used in the Shortcuts app UI like in a DeleteIntent (see my feedback about this: FB23451186 for more context). In the “Accelerating app interactions with App Intents” sample code we can see that this is done using a .stringsdict file, as follows for the “Trail” key (singular and plural): <key>Trail</key> <dict> <key>NSStringLocalizedFormatKey</key> <string>%#@VARIABLE@</string> <key>VARIABLE</key> <dict> <key>NSStringFormatSpecTypeKey</key> <string>NSStringPluralRuleType</string> <key>one</key> <string>Trail</string> <key>other</key> <string>Trails</string> </dict> </dict> I want to use a String catalog instead of a .stringsdict file because all my strings are in a String catalog. I tried to migrate the AppIntents.stringsdict file manually but it failed with an error: “An error occurred when migrating AppIntentsSampleApp/Resources/AppIntents.stringsdict: This stringsdict cannot be migrated: Missing required key 'NSStringFormatValueTypeKey' inside 'Trail' -> 'VARIABLE’” So I manually added a NSStringFormatValueTypeKey like this in the .stringsdict file: <key>Trail</key> <dict> <key>NSStringLocalizedFormatKey</key> <string>%#@VARIABLE@</string> <key>VARIABLE</key> <dict> <key>NSStringFormatSpecTypeKey</key> <string>NSStringPluralRuleType</string> <key>NSStringFormatValueTypeKey</key> <string>lld</string> <key>one</key> <string>Trail</string> <key>other</key> <string>Trails</string> </dict> </dict> And then I’ve been able to migrate the .stringsdict file into a String catalog. The string catalog looks like this after migration: "Trail" : { "extractionState" : "stale", "localizations" : { "en" : { "stringUnit" : { "state" : "translated", "value" : "%#@VARIABLE@" }, "substitutions" : { "VARIABLE" : { "formatSpecifier" : "lld", "variations" : { "plural" : { "one" : { "stringUnit" : { "state" : "translated", "value" : "Trail (Catalog)" } }, "other" : { "stringUnit" : { "state" : "translated", "value" : "Trails (Catalog)" } } } } } } } } This works, which is nice. But I tried to reproduce the same result by having a %#@VARIABLE@ in my LocalizedStringResource defaultValue like this: TypeDisplayRepresentation( name: LocalizedStringResource( "Flower", defaultValue: "%#@VARIABLE@", table: "AppIntents" ), numericFormat: LocalizedStringResource( "\(placeholder: .int) flower", table: "AppIntents" ) ) But the String catalog doesn’t support that apparently, I can’t get a “substitution” object in my catalog, so I have to manually do it using the source code which is not ideal and painful. Is there a way to support this kind of substitution with no actual plural token in the string as we can see for the %#@VARIABLE@ for Trail? Thank you, Regards, Axel

On this talk: Bring an LLM provider to the Foundation Models framework URL: https://developer.apple.com/videos/play/wwdc2026/339/ on the coding examples a very peculiar framework is shown: import MLXFoundationModels However I am not able to find it nowhere, there is even a code section with this framework as part of an example. Where is this framework, there are no BETA branches on the MLX framework either. Thanks!

In the WWDC 2026 sessions it was called out in code that the helper functions would still work, however they don't seem to be working either inside a UIViewRepresentable, nor as a UIKit View as below (also tried as a sheet, to no avail). Otherwise it works. Is there something else I'm missing? import SwiftUI import ImagePlayground @available(iOS 27.0, *) final class ImagePlaygroundPopupController: UIViewController { var sourceImage: UIImage var prompt: String var onComplete: (URL) -> Void var onCancel: () -> Void private var didPresent = false private var playgroundVC: ImagePlaygroundViewController? init( sourceImage: UIImage, prompt: String, onComplete: @escaping (URL) -> Void, onCancel: @escaping () -> Void ) { self.sourceImage = sourceImage self.prompt = prompt self.onComplete = onComplete self.onCancel = onCancel super.init(nibName: nil, bundle: nil) view.backgroundColor = .clear } required init?(coder: NSCoder) { fatalError("init(coder:) has not been implemented") } override func viewDidAppear(_ animated: Bool) { super.viewDidAppear(animated) guard !didPresent else { return } didPresent = true let vc = ImagePlaygroundViewController() vc.sourceImage = sourceImage vc.concepts = [.text(prompt)] vc.delegate = self playgroundVC = vc present(vc, animated: true) } } @available(iOS 27.0, *) extension ImagePlaygroundPopupController: ImagePlaygroundViewController.Delegate { func imagePlaygroundViewController( _ imagePlaygroundViewController: ImagePlaygroundViewController, didCreateImageAt imageURL: URL ) { imagePlaygroundViewController.dismiss(animated: true) { self.playgroundVC = nil self.onComplete(imageURL) } } func imagePlaygroundViewControllerDidCancel( _ imagePlaygroundViewController: ImagePlaygroundViewController ) { imagePlaygroundViewController.dismiss(animated: true) { self.playgroundVC = nil self.onCancel() } } } @available(iOS 27.0, *) struct ImagePlaygroundPopupView: UIViewControllerRepresentable { let sourceImage: UIImage let prompt: String let onComplete: (URL) -> Void let onCancel: () -> Void func makeUIViewController(context: Context) -> ImagePlaygroundPopupController { ImagePlaygroundPopupController( sourceImage: sourceImage, prompt: prompt, onComplete: onComplete, onCancel: onCancel ) } func updateUIViewController( _ uiViewController: ImagePlaygroundPopupController, context: Context ) {} }

Hello, My (fictional) app has multiple app entities like a BookEntity and an AuthorEntity. There is a relationship between them: a book has an author. Because I implement the EntityPropertyQuery for the BookEntityQuery, it creates a “Find Book where...” intent. In this intent, I can filter the data by an author (AuthorEntity). But I can’t find a way to allow the user to select any author using the searchable modal usually presented to “choose” a parameter value from an intent for example. Right now, it shows: a menu with the suggestedEntities() authors if the AuthorEntityQuery implements this function. With no way to search even if the AuthorEntityQuery conforms to the EntityStringQuery. a menu with allEntities() authors if the AuthorEntityQuery conforms to EnumerableEntityQuery and does not implement the suggestedEntities(). With no way to search even if the AuthorEntityQuery conforms to the EntityStringQuery. nothing if suggestedEntities() is not implemented and allEntities() is also not implemented even if the AuthorEntityQuery conforms to the EntityStringQuery. So this means if I implement suggestedEntities(), my users have no way to choose any author not in the suggestions. It’s too limited. if I implement allEntities() but not suggestedEntities(), this could potentially be a lot of entities and it’s not always relevant because then the Shortcuts app with an AuthorEntity parameter will be created for allEntities(), and the UI with always show the full list of allEntities() when I have to pick an author (unless I build a specific DynamicOptionsProvider but this would mean I lose the suggestedEntities() for example. if I just conforms to EntityStringQuery, I can’t select any item at all for this filter (no menu to choose). You can check the attached sample code provided. I checked a bit other apps, for example the Photos app allows you to find a photo based on an album but it lists ALL the albums (which is a lot) with no way to search using string. I also check the Sofa app, it shows the list of SofaListEntity (which implements suggestedEntities() and conforms to EntityStringQuery and EntityQuery). It actually shows all the lists (confirmed by the developer) with no way to search. See attachements from the Sofa developer. Is there a way to support a search for a filter using a relationship conforming to the EntityStringQuery? Is there a way to specify a provider for a @Property of an entity like we can for a @Parameter? For example, I could provide a custom DynamicOptionsProvider for the @Property(title: “Author”) var author which would be independent from the AuthorEntityQuery used elsewhere (parameter intents + Shortcuts). Maybe you can suggest another way to implement this? Maybe I should not rely on a relationship but instead flatten the relationship in the BookEntity to add an “authorName” or “authorID”? I filed this feedback with a sample code: FB23453134 Thanks, Regards, Axel

Hello, I'm using a DeleteIntent in my app, but I can't get it to display "Delete {Books}" in the Shortcut apps. It always displays "Delete {Book}". It apparently uses the BookEntity typeDisplayRepresentation instead of using the intent entities parameter title ("Books") in the parameterSummary. For a "normal" AppIntent, the Shortcuts app uses the entities parameter title ("Books") in the parameterSummary. I filed a feedback: FB23451186 Regards, Axel

still no sign of the new siri no app no nothing im on the ios 27 beta 2 and iphone 15 pro max what is this apple

I'm seeing what appears to be different UISceneAppIntent behavior between iOS and Designed for iPad on macOS, and I'd like to confirm whether this is expected. I'm working on an iOS app that defines an AppIntent conforming to UISceneAppIntent from the AppIntents framework. The intent is handled by a scene delegate conforming to both UIWindowSceneDelegate and AppIntentSceneDelegate. On iOS, everything works as expected: If the app is launched for the first time from Shortcuts, the intent is available via connectionOptions.appIntent in scene(_:willConnectTo:options:). If the app is already running, scene(_:willPerformAppIntent:) is called. However, when running the same iOS app on macOS in Designed for iPad mode, the behavior is different: If the app is launched from Shortcuts, connectionOptions.appIntent is always nil in scene(_:willConnectTo:options:). If the app is already running, scene(_:willPerformAppIntent:) is never called, even though the application is successfully activated. Is this expected behavior? I noticed that the AppIntents framework explicitly marks both AppIntentSceneDelegate and UISceneAppIntent as unavailable on macOS: @available(iOS 26.0, tvOS 26.0, *) @available(macOS, unavailable) @available(watchOS, unavailable) public protocol AppIntentSceneDelegate : UISceneDelegate Since the app is running on macOS in Designed for iPad mode and still uses the iOS binary, I wasn't sure whether these scene-based APIs are expected to work in this environment or whether they are intentionally unsupported. Has anyone from Apple or the community been able to confirm whether this behavior is by design, or whether it should be considered a bug? I'd appreciate any clarification.

Actually trick to change language to English UK, restart and change back to English US worked for me. After this in an hour notification showed up and Siri AI was ready.

I live in Canada and I called apple support, they said the new Siri ai isn’t available in some parts of Canada. I’ve changed my region to united states and now it’s just a waiting game. If i now get it fast and quick I’ll let u guys know

In my app, I adopt ‘App Intents’ and ‘App Entities’ for various items and actions in my app. These work in the Shortcuts app, and users can use Find Intents to lookup information or use the intents to act up on them, even though they don’t map on to any of the specific App ‘Schemes’ and ‘Domains’ that are listed. If I'm using just App Entities and Intents on their own, would these participate with the new Siri AI, without any additional work? For example, in my app, I have entities like Contacts, Tags, and ‘Visit Logs’. I have intents for 'create tag’, ‘add tags to a contact’, add a ‘Log’ to a 'contact' etc. These are specified in the AppShortcutsProvider list, but I have more than 10 intents. How would these work with the new Apple Intelligence and Siri? Or does Siri integration require AppSchema adoption?