Apple Intelligence & AI in your iOS app
On-device AI is no longer a lab demo. Since iOS 18.4, Apple Intelligence is available in English. With iOS 26 and the Foundation Models framework, developers have access to a ~3 billion parameter language model running directly on the device — no API keys, no per-request costs, no internet connection required.
At AtalayaSoft we build intelligent features inside iOS apps: automatic summaries, content classification, conversational assistants, entity extraction and natural language-guided flows. With attention to what matters in production: native UX, reliability, user privacy and cost optimisation.
The mobile AI opportunity window
- Since iOS 18.4 (March 2025), Apple Intelligence is available in English, and with iOS 26 the Foundation Models framework opens Apple's on-device model to third-party apps.
- Apple's on-device model (~3 billion parameters) runs directly on the iPhone: no API keys, no per-request costs, and no internet connection.
- While demand for AI features explodes, the pool of native iOS developers with on-device AI experience is especially scarce. Finding profiles that combine deep native iOS with production LLM integration is not easy.
- Integrating on-device AI in your app now means shipping before your competition an experience that users already expect from their iPhones.
What we can build in your app
Features with Apple Foundation Models
Implementation of features using Apple's on-device model (~3B parameters): summaries, entity extraction, structured text generation, classification and tool calling. All with @Generable and @Guide macros for typed and predictable output.In-app conversational assistants
Design and implementation of conversational flows integrated into the app: support chatbots, navigation assistants, natural language search. With context management, fallbacks and native UX — not a WebView with a generic chatbot.Cloud LLM integration (Claude, GPT)
When the use case requires capabilities beyond the on-device model, we integrate LLM APIs such as Claude or GPT with robust error handling, intelligent caching, response streaming and per-request cost optimisation.Core ML and custom models
Integration of custom machine learning models via Core ML: image classification, object detection, sentiment analysis, recommendation models. Conversion from PyTorch/TensorFlow and optimisation for Apple Silicon.Privacy and local processing
Design of architectures that maximise on-device processing to comply with GDPR and user privacy expectations. Sensitive data never leaves the iPhone — AI runs where the data is. Designed with GDPR and EU AI Act in mind from day one.API cost optimisation
Strategies to reduce AI API costs: response caching, batch processing, on-device models for simple tasks and cloud APIs only for complex tasks. Hybrid architecture balancing capability and cost.Technical stack
Apple on-device AI
- Foundation Models (iOS 26)
- Apple Intelligence APIs
- Core ML
- Writing Tools
- Image Playground
- Visual Intelligence
Cloud LLMs
- Claude API (Anthropic)
- OpenAI API
- Response streaming
- Function calling / tool use
Machine Learning and custom models
- PyTorch → Core ML
- TensorFlow → Core ML
- ONNX
- Core ML Tools
How we approach an iOS AI project
We start not with the technology, but with the problem we want to solve for the user:
-
01. Use-case definition
We start not with the technology, but with the problem. What intelligent feature would bring real value to the user? Does it need on-device or cloud processing? What is the expected volume? What privacy constraints exist?
-
02. Functional prototype
We build a rapid prototype that demonstrates technical feasibility and user experience. This allows validating the concept before investing in the full implementation.
-
03. Production implementation
Development of the feature with robust architecture: error handling, timeouts, fallbacks, caching, monitoring and automated testing. AI in production needs the same engineering as any critical feature.
-
04. Optimisation and measurement
Monitoring of usage metrics, latency, API costs and user satisfaction. We iterate on prompts, model parameters and UX based on real data.
Companies we have worked with
Our experience in large-scale production iOS apps comes from working with enterprise teams such as Banco Santander, Zara/Inditex, AXA and Juegos ONCE. That technical foundation — clean architecture, testing, security and accessibility — is what we now apply to Apple Intelligence, Foundation Models and production LLM integrations.
Ready to add AI to your iOS app?
Tell us about your use case and we will design the best technical solution together — no commitment.
Testimonials
The team working on your project
Go deeper into Apple Intelligence
Francisco has published detailed technical analyses on Apple's on-device AI announcements: