Working with Platform Specific Libraries in KMP

Kotlin Multiplatform (KMP) is rapidly gaining traction, with an increasing number of developers adopting it for cross-platform development. While the library ecosystem for KMP is expanding, there are still cases where we need to rely on native libraries due to gaps in multiplatform support. Fortunately, native libraries in Kotlin are robust, and we can take advantage of them, even when KMP support is limited.

In this session, I'll demonstrate how to seamlessly integrate existing native libraries into your KMP projects. Using examples like the Amazon Kotlin SDK, which supports Android and Desktop but not iOS, I’ll walk through practical strategies for leveraging native solutions effectively while maintaining a shared codebase. Join me to explore how to bridge the gaps in the KMP library ecosystem with native libraries.

Prompt Engineering Unleashed: A Journey from Beginner to Pro

This talk offers a comprehensive guide to prompt engineering, the critical skill of crafting effective instructions for large language models. We'll start with a foundational "Prompting 101" session, perfect for beginners looking to demystify how AI models interpret and respond to queries. You'll learn the core principles of crafting clear and concise prompts and the anatomy of a good prompt.

From there, we will quickly elevate to intermediate and advanced techniques. We will explore more complex strategies like few-shot prompting, chain-of-thought, and leveraging system prompts to fine-tune model behavior. The talk will include real-world examples and practical tips for debugging and iteratively improving your prompts for more reliable and high-quality outputs. Whether you're just starting out or are looking to level up your AI skills, this session will provide you with the tools to master the art and science of communicating with AI.

Run Gemma Locally on Android in 10 Minutes

Want to run a real LLM completely offline on Android? In this lightning talk I’ll show you the fastest practical path to get Google Gemma working on your device today.

You’ll see:

The quickest way to test Gemma locally using Media Pipeline
How to pick the right quantized model
The minimal code needed to integrate it into an Android app with MediaPipe / LiteRT-LM
Key performance tips and common pitfalls

In 10 minutes you’ll go from zero to running a local LLM on Android — no cloud, no API keys, no data leaving the device.

No Wi-Fi, No Problem: On-Device AI with Kotlin Multiplatform

Put your phone in airplane mode. Now ask your app a question—and watch it answer.
In this hands-on session, we’ll build an AI-powered Kotlin Multiplatform app that runs Gemma models directly on Android and iOS. No API keys, no inference server, and no internet connection once the model is downloaded.
We’ll follow the path from choosing a model that fits in your pocket to streaming its first response. Along the way, we’ll explore what belongs in shared Kotlin code, what needs a platform-specific implementation, and how to connect native inference runtimes behind a common API.
Then we’ll tackle the details that make or break the experience: large downloads, slow model loading, memory limits, battery use, and devices that perform very differently from your development phone.
Expect live demos, real Kotlin code, and an honest look at the trade-offs. You’ll leave with a repeatable approach to bringing offline AI into your own KMP apps.
Learning outcomes
- Choose a Gemma model and quantization appropriate for mobile devices.
- Design a shared Kotlin API around platform-specific inference engines.
- Stream model responses into a Compose Multiplatform UI.
- Manage model downloads, loading states, and resource lifecycles.
- Measure performance and understand the trade-offs on real devices.

Getting start with KMP

As Kotlin Multiplatform (KMP) and Compose Multiplatform (CMP) continue to gain traction, and with increasing support from many Android libraries, developers are eager to learn how to dive into these technologies and understand the ecosystem.
In this session, I will cover:
- What is KMP How to get started and the different templates available
- Working with Expect and Actual
- The ecosystem and available libraries
- What is Compose Multiplatform

TDD in Android

In this workshop, we will be going through the TDD process and we will be adding some features to an application.

IntelliJ Plugin Development

In this session, I will cover IntelliJ IDE plugin development, how you can start with plugin development, and what are different options available.
Also, will also cover how you can automate your model creation with your custom plugin.

Elevate Your Cross-Platform App Animations: A Compose Multiplatform Adventure

In this informative session, we will explore the art of creating captivating animations using Compose Multiplatform. Taking inspiration from Roaa Kadam's widely acclaimed Flutter Vikings Talk, "Take Your Flutter Animations to The Next Level," we will adapt these principles to Compose Multiplatform.

Our agenda covers four key areas:

Animating ScrollView: Learn how to infuse life into your app's scroll behavior, making it visually engaging and interactive.

Complex Hero Animations: Discover techniques for crafting intricate hero animations that smoothly transition between screens and elements.

Gyroscope Effect for All Devices: Explore the implementation of gyroscopic effects on mobile devices and an alternative approach for non-mobile platforms, ensuring a consistent user experience across the board.

MouseRegion Animation: Extend your animations to desktop platforms with MouseRegion interactions, providing a gyroscopic-like experience for a broader audience.

Developing Music App in KMP

In this session, we will cover an intro to the KMP and Compose Multiplatform and then will go through how you can access platform-specific APIs on each platform like Android, iOS, Web and Desktop.

Building Reflective UI in Compose Multiplatform (KMP)

In this engaging session, I will provide an insightful introduction to Compose Multiplatform and Kotlin Multiplatform (KMP). We'll delve into the exciting world of cross-platform development and explore how you can seamlessly access platform-specific APIs like Camera across a range of frameworks, including Android, iOS, Web, and desktop. I'll guide through the process of harnessing the power of KMP to tap into functionalities such as Camera feed access. Additionally, we'll explore the art of creating a dynamic and reflective user interface that adapts beautifully to diverse platforms.

Building Music App with Compose Multiplatform

In this session, I will provide a comprehensive overview of Compose Multiplatform and demonstrate its real-world application by building a multi-platform music player. We will explore the exciting possibilities of creating a single codebase that can run on Android, iOS, Web, and Desktop, while also covering how to effectively utilise platform-specific APIs within the Compose framework. Along the way, I'll walk you through the intricacies of making API calls and implementing seamless navigation in your multiplatform projects. By the end of this talk, you'll have a clear understanding of how to harness the potential of Compose Multiplatform to develop cross-platform applications efficiently and effectively.

Automate Models Creation with IntelliJ Plugin

At SWVL, we reduced our model creation and mapping of different data layers from 40 minutes to just 1 minute. We achieved that by extending a plugin and using some file templates mechanism. In this session, we will be covering IntelliJ Plugin Development, file templating and mapping model creation.

Welcome to KMP World

In this workshop, we will be creating a basic application that can run on Android, iOS, Web, and Desktop platforms. Furthermore, we will introduce you to the world of KMP.
We will delve into the steps involved in making API requests, loading images, and implementing navigation within the application.
Our main objective will be to develop a simple yet effective application that showcases the fundamental task of retrieving data from the network and displaying it.

Introducing KMP and performing a network call. Having a MAC is essential for running the iOS app, but it is not mandatory.
It is advisable to have IntelliJ and Fleet IDE set up, along with KDoctor, to ensure proper configuration.