Hi everyone,
I’m trying to understand the current capabilities of App Intents and Siri when using custom intents and custom entities, without adopting one of Apple’s predefined app schemas.
As an example, imagine I have a shopping app for shoes. I might have one intent that lists shoes available for sale, and another intent that can open a specific shoe in the app or add a specific shoe to favourites.
What I’m trying to validate is whether Siri can support multi-turn, contextual follow-up requests in this kind of custom-intent-only setup. For example:
- User: “Show me the shoes available for sale.”
- Siri/App: returns a list of shoes.
- User: “Add the third one to my favourites.”
- Siri understands that “the third one” refers to the third shoe from the previous result list.
This kind of follow-up seems to work in some Apple-defined domains. For example, a user can ask to list calendar events and then follow up with something like “open the third one in Calendar,” and Siri appears to understand the reference to the previous list item.
My current understanding is that this kind of conversational context, ordinal reference resolution, and follow-up disambiguation may only be available when adopting one of Apple’s app schemas, where Siri has a richer understanding of the domain and entities.
If an app only uses custom App Intents and custom App Entities, without adopting an Apple-defined schema, should we expect Siri to support this kind of multi-turn reference resolution? Or is each turn in the conversation which requires a custom intent invocation effectively handled more independently?
I’d appreciate any clarification on whether this is expected to work, currently unsupported, or only available through schema-based integrations.
Thanks