Custom vocabulary for speech and entity resolution

Whisper and other STT APIs let you pass a custom vocabulary or initial_prompt to bias recognition toward domain-specific proper nouns. In the App Intents / Siri stack, is there an equivalent way to supply dynamic, per-user term lists — for example favorites or recently used items — to improve how spoken names are transcribed or resolved?

Topic: Machine Learning & AI SubTopic: Foundation Models

1

0

342

Jun ’26

RAG boundary: static knowledge vs live data

Should static domain documentation live in on-device RAG (local embeddings + FM), while time-sensitive data always comes from network tools — and are there practical size/latency budgets for on-device embedding indexes?

Topic: Machine Learning & AI SubTopic: Foundation Models

1

0

185

Jun ’26

Tool calling: App Intents vs server-side orchestration

For assistants that need multi-step tool use (search → fetch → compare → respond), should third-party apps expose capabilities as App Intents for on-device model selection, or keep tool orchestration on the server and use on-device models only for speech and summarization? What breaks when the same action exists in both places?

Topic: Machine Learning & AI SubTopic: Foundation Models

1

0

212

Jun ’26

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?

Topic: Machine Learning & AI SubTopic: Foundation Models

1

0

160

Jun ’26

Disambiguation when multiple entities match

When a spoken phrase could match several entities in our catalog — same region, similar names, or partial matches — who is responsible for disambiguation: Siri via App Schemas and entity resolution, or the app via EntityStringQuery returning multiple candidates? What’s the recommended UX pattern for ‘Did you mean A or B?’

Topic: Machine Learning & AI SubTopic: Foundation Models

5

0

212

Jun ’26

Siri without opening the app

Can App Intents perform authenticated backend calls (Bearer token in Keychain / App Group) and return structured results to Siri, or must execution always launch the host app first?

Topic: Machine Learning & AI SubTopic: Foundation Models Tags: App Intents

1

0

172

Jun ’26

Privacy, personalization, and App Store expectations

We offer both cloud-based AI (subscription) and are exploring on-device Apple Intelligence features. What user profile data is appropriate to inject into on-device model sessions under Apple’s privacy guidelines, and how should apps disclose hybrid cloud + on-device AI in privacy nutrition labels and review?

Topic: Machine Learning & AI SubTopic: Foundation Models

1

0

132

Jun ’26

Summarization that must not hallucinate numbers

What’s Apple’s guidance for using on-device models to turn structured JSON (time series, metrics, units) into a one-line natural-language summary without inventing values?

Topic: Machine Learning & AI SubTopic: Foundation Models

1

0

90

Jun ’26

React Native + native AI bridge

What’s the supported integration path for Foundation Models and Apple Intelligence from a React Native app — thin Swift native module, App Intents only, or are these features effectively Swift-first?

Topic: Machine Learning & AI SubTopic: Foundation Models

2

0

83

Jun ’26

In-app text input vs system speech paths

If users dictate into a standard TextField via the keyboard mic instead of a dedicated in-app record button, does that text still benefit from App Intents entity resolution and indexed entities — or is keyboard dictation a separate pipeline where we lose domain vocabulary unless the user invokes Siri directly?

Topic: Machine Learning & AI SubTopic: Foundation Models

0

1

63

Jun ’26

Mixed languages and foreign proper nouns

If the user’s device language is French but they speak English, or they use one language for the sentence and another for proper nouns, how does Siri handle transcription and entity resolution? Do we need per-locale entity indexing, aliases, or can semantic indexing work across languages?

Topic: Machine Learning & AI SubTopic: Foundation Models

0

0

63

Jun ’26

Speech recognition with large, dynamic vocabularies

Our users speak proper nouns and domain terms (place names, product jargon) that change frequently. What’s the best practice for improving recognition accuracy: dynamic contextual strings, on-device custom language resources, periodic vocabulary sync, or something else in the current Speech APIs?

Topic: Machine Learning & AI SubTopic: Foundation Models

1

0

95

Jun ’26

Hybrid assistant architecture (on-device model + server tools)

We run a conversational assistant where answers depend on live API data, not just static knowledge. What is Apple’s recommended split between on-device Foundation Models (intent, routing, summarization, privacy-sensitive context) and server-side tool execution? Is there an official pattern for a local planner with a remote executor?

Topic: Machine Learning & AI SubTopic: Foundation Models

0

0

62

Jun ’26

Resolving server-backed entity catalogs

For large, frequently updated catalogs that live on a server, should Siri resolution use EntityStringQuery with disambiguation, or is IndexedEntity required for acceptable quality in the car?

Topic: App & System Services SubTopic: CarPlay

1

0

561

Jun ’26

Authentication across app extensions

If the main app requires sign-in, what’s the recommended pattern for sharing auth/session state with widget or watch extensions so users aren’t prompted to log in again when tapping a widget?

Topic: UI Frameworks SubTopic: SwiftUI

0

0

38

Jun ’26