World Congress 2025 Aug 20, 2025 Session details

Harnessing Apple Intelligence: Live Coding with Swift for iOS

MIlan Todorović

Ditch external APIs and run a 3-billion-parameter LLM locally on iOS. This live coding demo reveals how simple Swift code unlocks Apple Intelligence for private, on-device text generation.

Pause
Mute Enter Fullscreen
#1 about 2 min

Introduction to the Apple Intelligence developer ecosystem

An overview of Apple Intelligence as the unified umbrella for all generative AI capabilities across Apple platforms.

#2 about 1 min

Apple's privacy-first approach to on-device processing

Why executing compute workloads on-device is critical for protecting user data and minimizing remote network risks.

#3 about 5 min

Implementing machine learning with Core ML and Vision

A breakdown of existing purpose-built frameworks for device-optimized model execution, natural language, and image processing tasks.

#4 about 2 min

Training and fine-tuning models natively using MLX

Using the MLX framework framework to train, tune, and test machine learning models seamlessly on Apple Silicon hardware.

#5 about 3 min

Exploring generative intelligence features and App Intents

How system-wide AI enhancements integrate deeply into existing software applications through functional extensions and App Intents.

#6 about 2 min

Comparing local foundation models to cloud-based language models

Assessing the practical capabilities of localized foundation models utilizing three billion parameters against larger network-based architectures.

#7 about 7 min

Setting up a native SwiftUI application in Xcode

Creating a new cross-platform Swift project utilizing AI-assisted completion features and user interface states available in newer developer environments.

#8 about 4 min

Implementing language model sessions using Swift asynchronous coding

Importing foundational libraries and structuring asynchronous Swift execution tasks to safely query local language model sessions.

#9 about 3 min

Testing entity extraction via the on-device language model

Commanding the local language model to dynamically extract specific personal names from unstructured historical text blobs.

#10 about 5 min

Configuring system prompts utilizing Apple developer API documentation

Exploring official API references to properly parameterize standard foundation models using structured intent variables and conversational prompts.

Matching moments

40 sec

Navigating Apple's evolving on-device AI and machine learning stack

Precious Osaro Precious Osaro · WWC Europe 2026

4:12 min

Shifting from AI features to AI-assisted iOS development

MIlan Todorović MIlan Todorović · WWC Europe 2026

2:08 min

Reviewing Xcode implementations and Vision framework documentation reference resources

Milan Todorovic · WWC 2021

4:52 min

Understanding the iPhone moment of software engineering

Mike Swift · Coffee With Developers

2:41 min

Leveraging AI tooling for accelerated learning and productivity

Dan Mindru · Coffee With Developers

2:25 min

Testing the AI generated Apple iOS Flashcards application

MIlan Todorović MIlan Todorović · WWC Europe 2026

Upcoming sessions on this topic

Open session

World Congress 2026 North America

From Software Agents to Physical Devices: Inside the Agentic Hardware Stack

Michael Yuan, Vivian Hu

Michael Yuan
Vivian Hu
Open session

World Congress 2026 North America

Small LLM in your Browser: Huge Opportunities for Web Applications

Daniel Ostrovsky

UI/UX Architect at Payoneer | AI Architect | Full Cycle Development Expert | Public Speaker | Open Source Contributor |

Daniel Ostrovsky
Open session

World Congress 2026 North America

Vibe Coding Accessibility

Karl Groves

Focused on actively fixing accessibility

Karl Groves
Open session

World Congress 2026 North America

Building Stuff with GenAI - The Open Minded Workshop beyond OpenAI

Andreas Erben

CTO for Applied AI and Metaverse at daenet

Andreas Erben
Open session

World Congress 2026 North America

The Things Your AI Isn't Telling You

Desmond Lamptey

Lead Software Engineer @ Capital One

Desmond Lamptey
Open session

World Congress 2026 North America

Ship 10x Faster: AI-Powered Development with Claude Code and MCP Tools

Viktoria Semaan

Principal Technical Evangelist at Databricks

Viktoria Semaan