I don't have the time or bandwidth at the moment to test this out, but I am going to throw this idea out there in case it might help unblock some other engineers with Siri AI integrations in their app. In the App Intents Q&A, there were two things that the Apple engineers repeatedly stressed: Discoverability of entities does not require conforming to the whitelisted schema domains. Siri can only take actions that do conform to the whitelisted schema domains. What this says to me is that one potential path forward for integrating your app's entities and actions with Siri AI agentically at launch might be to (1) expose your custom entities using the various discoverability features, and then (2) add an agent directly into your app that can take actions on your users' behalf, exposing intents to Siri that allow Siri to message that agent, conforming the relevant intents to the Messages App Schema Domain. I haven't tested this, but it looks like it should theoretically be possible with the APIs I'm aware of. If someone has the chance to test this and report their findings, I get the impression that a lot of other developers would be thankful. It's a bit heavier-weight of a solution than I would have liked, but does represent additive functionality that could be useful to your users, as you could expose your custom agent directly to your users within your app, giving them a new way to interact with the functionality you provide, in addition to the added benefits that come from integrating with Siri AI directly.

I attended the Apple Intelligence Group Lab and the only positive thing I can say is that I appreciate the empathy that James Paolantonio displayed when presented with developers who are understandably frustrated by the limitations imposed by the very narrow scope of the whitelisted schema domains.

I'll be at the Apple Intelligence session, and I will do the most I can with the 300-character limit, but I hope you appreciate that it's not really a forum in which a conversation is possible, as 300 characters really isn't enough to convey the scope of the issue (which is why I refer to Apple's sample code as a useful shorthand - even here, it illustrates the same concept clearly without me posting a ton of new explanation), there's no opportunity for back-and-forth in those sessions, and the time limit and audience size means that it's not really even likely my question gets surfaced. If you want to help, you could also attend the session and boost my question when you see it: "My app's core entities and actions don't map to any predefined schema domain, like the apps of many others. What's the best way to bring them to the new agentic Siri today, what should I do now to be ready as the platform evolves, and how do you think about their place in the agentic experience?" I also don't recommend filing a bug, which is why I filed my feedback as a Suggestion in Feedback Assistant, and I recommend others do the same. Once we can hear more about what the actual intent is, then we know for sure whether what has launched / is docuemnted matches intention, as well as whether intention matches developer requirements.

I have the same question, and after watching the sessions I think the answer is clearer than the thread suggests, which is part of why I wanted to raise it here. I watched Build intelligent Siri experiences with App Schemas along with sessions 345 and 343. My read is that they're consistent and explicit: to expose your entities and actions to the new Siri and the agentic features, those entities have to conform to the published App Schemas. If your data doesn't fit one of the whitelisted domains, there's no supported path. Here's the concrete version. Apple's own sample, Defining app entities for your custom data types, builds a hiking app with a TrailEntity. A TrailEntity maps to none of the published domains. So a user with that app can't ask Siri to compare routes or pick a trail, and there's nothing the developer can do to enable it. Most apps with interesting custom data are in the same position. As it stands, that leaves a large part of the third-party ecosystem out of the agentic experience, and it leaves users believing Siri is still the unreliable assistant it has long been reputed to be. I want to be constructive about this. The beta only just shipped, so this is still a decision that can change before the public release. A few things that would make a real difference: Give developers clear guidance on how to annotate entities and actions now, even without a matching domain, so the work becomes useful when the restriction is lifted. Let developers define or propose their own domains. Let the on-device model infer a domain from a well-annotated entity when there's no exact match. I filed this as FB23018652 with the TrailEntity example. If this affects your app too, filing your own feedback and boosting this thread would help it get a real answer while there's still time to change it.