How Google Uses Kotlin

Real-time AI agents break traditional request-response load balancing paradigms because they rely on long-lived, stateful bidirectional streams that obscure true server capacity. To solve this, developers must implement application-level session tracking directly within the runtime to accurately measure the committed concurrent workload of active conversations. By feeding these precise session counts alongside standard CPU utilization metrics into a hybrid routing algorithm, infrastructure can effectively distribute stateful AI traffic and prevent individual backend bottlenecks.

Answering the questions of "why we built ADK 2.0". This explains the rationale, some of the features, and why a developer should consider upgrading. This will be published the day after ADK go 2.0 launches.

We are excited to bring Express checkout with Google Pay for Android native apps enabling developers...

Google has announced the launch of version 0.1.0 of the Agent Development Kit (ADK) for Kotlin, alongside a specialized ADK library for Android. This open-source framework simplifies the creation of AI agents by managing complex orchestration, session sharing, and error handling across cloud and edge environments. The release supports hybrid orchestration, enabling developers to build multi-agent systems where a cloud-based model can seamlessly offload specific tasks to local, on-device models like Gemini Nano to enhance user privacy.

Google announced the transition from assistive AI to independent agents, highlighting the launch of the Gemini 3.5 series and major updates to its Antigravity agent-first development platform. For mobile developers, the post introduces new Android CLI tools, the Android Bench evaluation leaderboard, and an automated Migration agent designed to rapidly convert various frameworks into native Kotlin code. Web development is also being transformed through Chrome DevTools for agents, the HTML-in-Canvas API, and the proposal of WebMCP, an open web standard that enables browser-based AI agents to execute complex tasks.

Google AI Edge’s LiteRT-LM provides a production-proven, highly optimized infrastructure for running Gemma 4 across cross-platform mobile and edge environments. It actively unlocks the model's native multimodal and agentic features on-device by utilizing memory-efficient dynamic loading, Multi-Token Prediction for up to a 2.2x speedup, and advanced orchestration tools like Thinking Mode and Constrained Decoding. Furthermore, the engine is rapidly expanding its integration surfaces beyond Android, introducing new native Swift APIs for Apple ecosystems and WebGPU-accelerated JavaScript APIs for high-performance, serverless browser inference.

LiteRT is a production-ready framework designed to help mobile developers unlock the power of Neural Processing Units (NPUs), overcoming the performance and battery limitations of traditional CPU or GPU processing. By providing a unified API that abstracts away hardware complexities, it allows industry leaders like Google Meet and Epic Games to deploy sophisticated AI models for real-time video, animation, and speech recognition with significantly higher efficiency. The platform further supports developers through benchmarking tools and cross-platform compatibility, enabling seamless AI deployment across mobile devices, AI PCs, and industrial IoT hardware.

The newly introduced continuous checkpointing feature in Orbax and MaxText is designed to optimize the balance between reliability and performance during model training, addressing issues with conventional fixed-frequency checkpointing. Unlike fixed intervals—which can either compromise reliability or bottleneck performance—continuous checkpointing maximizes I/O bandwidth and minimizes failure risk by asynchronously initiating a new save operation only after the previous one successfully completes. Benchmarks demonstrate that this approach significantly reduces checkpoint intervals and results in substantial resource conservation, especially in large-scale training jobs where mean-time-between-failure (MTBF) is short.

The article discusses the advancements in on-device AI powered by MediaTek's Neural Processing Unit (NPU) and the introduction of the LiteRT NeuroPilot Accelerator.

The article discusses optimizing performance on Qualcomm's Neural Processing Unit (NPU) using LiteRT, Google's high-performance on-device ML framework.

The article discusses the deployment of on-device generative AI (GenAI) using LiteRT-LM in Chrome, Chromebook Plus, and Pixel Watch.

The article discusses the integration of Google Pay within Android WebView, highlighting its availability starting from WebView version 137.

The article celebrates Flutter's evolution into a production-grade app framework, highlighting its widespread adoption and the vibrant community that supports it.

The article introduces the developer preview of the Android XR SDK, a comprehensive toolkit designed for creating applications that leverage extended reality (XR) on Android devices.

The article discusses Kotlin Multiplatform (KMP) and its applications in cross-platform development, highlighting Google's adoption of KMP in its products and the insights shared during KotlinConf ...

The article recaps the Google I/O 2024 event, highlighting advancements in AI technologies aimed at making AI accessible for developers.

The article discusses how Google is simplifying cross-platform development for developers by recommending specific technologies and frameworks.

The article introduces Gemini Pro, Google's latest AI model designed for developers and enterprises, highlighting its capabilities, integration options, and pricing.

KAYAK successfully integrated passkeys into their Android and web applications, achieving a 50% reduction in sign-in time and enhancing security.

The article highlights the experiences of developers using Google tools and Bard in their projects.

The article introduces an updated Google Pay button view for Android, enhancing customization and integration capabilities for developers.

Google I/O 2023 is set to begin on May 10, featuring keynotes and sessions focused on Modern Android Development, multi-device experiences, and platform quality.

The article discusses the introduction of Java 11 support for Google Cloud Functions, allowing developers to write serverless functions in Java.