Structured intents vs free-form queries

For voice assistants with many capabilities, is it better to ship one generic ‘ask assistant’ intent with a natural-language parameter, or many typed intents (GetForecast, CompareLocations, etc.)? What are Siri’s limits on disambiguation and follow-up turns?

Thanks for your question. This QA session focuses on the Foundation Models framework. Your question is related to App Intents and Siri, and so we suggest that you ask in the main forums for folks with expertise in that area to comment.

Structured intents vs free-form queries
 
 
Q