{"slug": "from-in-app-agents-to-the-android-intelligence-system-whats-new-in-intelligent", "title": "From in-app agents to the Android intelligence system: What’s new in intelligent apps at the Android Developer Summit", "summary": "Google unveiled Android MCP, a unified tool-calling framework powered by the AppFunctions Jetpack library, at the Android Developer Summit, letting developers connect apps to on-device AI agents including the Gemini system agent. Google also opened a Connected Apps Platform preview program for direct app connections through the Gemini app and Google Search on Android, and expanded ML Kit GenAI APIs to support agentic workflows entirely on-device using Gemini Nano 4's new function calling. The company published 10 new on-demand sessions covering the intelligent-apps tooling.", "body_md": "[Product News](https://developer.android.com/blog/categories/product-news)\n\n# From in-app agents to the Android intelligence system: What’s new in intelligent apps at the Android Developer Summit\n\n4 min read\nIn the intelligence era, users are no longer just tapping through apps, they express high-level goals and expect AI agents like Gemini to complete multi-step workflows, sometimes across multiple apps on their devices. To help you meet users where they are, we’re unlocking new ways to build intelligent, agentic experiences in your Android apps:\n\n- **Connect with the Android intelligence system:** Share your app’s capabilities with the system agent with Android MCP. To let users connect directly with your app through the Gemini app and Google Search on Android, join the Connected Apps Platform preview program.\n- **Bring intelligence into your app:**  Build smart features and agents on-device with ML Kit GenAI APIs, bring your custom ML model with LiteRT in Google Play services. Leverage Gemini models on the Cloud with Firebase AI Logic, and enable your agent to build native Compose UI with the A2UI Compose renderer.\n\nYou’ve already seen some of these new APIs and developer tools at the [__Android Developer Summit keynote__](https://youtu.be/8Lmv7LGgL4E). Now, learn with our new deep-dive resources to help you build intelligent apps, including [__10 new on-demand sessions__](https://goo.gle/ADS26-Intelligent-Apps) around new intelligent experiences.\n\n## Connect with the Android intelligence system\n\nThe Android intelligence system is the system foundation designed to protect users while connecting AI agents with apps on Android devices. It provides users with both prompted assistance and proactive assistance across the Android ecosystem of devices spanning phones, wearables, XR glasses, TVs, and automobiles.\n\n- **Prompted assistance** : When the user actively asks an agent to fulfill a goal (for example, \"check my calendar, book a ride, and message Jingyu my ETA\"), the agent orchestrates tools across apps to get it done. For the fastest, most reliable execution, you can use a[__remote MCP__](https://developers.google.com/connected-apps/mcp) server or local[__Android MCP__](https://developer.android.com/ai/appfunctions) . Agents can also fall back to using Android’s[__Computer Control framework__](https://developer.android.com/ai/computer-control) to complete actions without requiring any app-side integration.\n- **Proactive assistance** : The system anticipates the user's needs and surfaces contextual suggestion chips directly on lock screens, notifications, virtual keyboards, and within apps.\n\nWe give you control over how your apps [__integrate with the Android intelligence system__](https://developer.android.com/ai/intelligence-system) by providing APIs and tools based on the familiar [__MCP__](https://modelcontextprotocol.io/docs/2026-07-28/getting-started/intro) standard. [Android MCP](https://developer.android.com/ai/appfunctions), powered by the [__AppFunctions Jetpack library__](https://developer.android.com/jetpack/androidx/releases/appfunctions), is our unified tool-calling framework. It lets you connect with qualified AI agents right on the device, whether the system agent or your own on-device in-app agent. Remote MCP server provides you with cross-platform reach. \n\nAndroid MCP complements remote MCP as an Android native solution and is the recommended integration path when your user journey uses end-to-end encryption or sensitive local device data, requires device sensors and hardware, needs to execute locally, or when there’s no server endpoint available.\n\nTo learn more about the Android intelligence system and integrate with Gemini as the system agent, watch this talk:\n\n## Bring intelligence into your apps: from on-device agent to A2UI Compose renderer\n\nWith new capabilities available in Gemini Nano 4 like function calling, we are expanding the ML Kit GenAI APIs to build agentic workflows entirely on-device. We provide you the building blocks directly with ML Kit’s [__direct model access__](https://developers.google.com/ml-kit/genai/prompt/android) with Prompt API and the new [__Agentic API__](https://developers.google.com/ml-kit/genai/agent/android) that auto-executes functions for you, saves conversation history, manages the orchestration loop, and includes automatic guardrails. Check out the [__Jetpacker code sample on GitHub__](https://github.com/android/ai-samples/tree/main/jetpacker) and watch this video for a deep dive into how you can unlock agentic capabilities in your app with ML Kit GenAI APIs: \n\nBesides the new Agentic APIs, we are bringing a suite of new capabilities on-device:\n\n- Get an overview of [__on-device ML Kit GenAI APIs__](https://youtu.be/p-SZ1rWvErU?si=fjNFcsIOc7mufrws) , from Prompt API features like[__thinking mode__](https://developers.google.com/ml-kit/genai/prompt/android/thinking-mode) and[__system instructions__](https://developers.google.com/ml-kit/genai/prompt/android/system-instructions) to new alpha APIs like the[__Embeddings API__](https://developers.google.com/ml-kit/genai/embedding/android) , powered by[__EmbeddingGemma 2__](https://huggingface.co/google/embeddinggemma-2) . You'll also learn about under-the-hood Android system optimizations and see common on-device GenAI use cases already in production.\n- Take a [__deep dive into the model architecture__](https://youtu.be/ekS4_gV6Ojc?si=tb5P_Cdslh_r85YQ) of Gemini Nano 4, built on Gemma 4. Powered by per-layer embeddings, quantization-aware training, and multi-token prediction, Gemini Nano 4 delivers to 3x inference speedup while cuts memory usage by up to 4x compared to the previous version of Gemini Nano model under internal testing benchmarks.\n- You can run your custom ML models with faster GPU performance using [__LiteRT in Google Play services__](https://developer.android.com/ai/custom) which removes the runtime from your APK making your APK about 8 MB smaller. Now also available on Wear OS and Android Automotive OS. Whether you are using the turn-key ML Kit APIs or bring your own custom edge model, read the [__announcement__](https://developers.googleblog.com/smaller-apps-and-faster-gpu-inference-with-litert-in-google-play-services/) and check out this[__talk__](https://youtu.be/LiBWWJ9IKag?si=1W7NnRg90Bgjwhwc) .\n- See how these APIs come together in real-world apps, from an [__XR language teacher__](https://youtu.be/tW3mg0iyi_w?si=6pZugc8ifajQJTKy) using the ML Kit[__speech recognition__](https://developers.google.com/ml-kit/genai/speech-recognition/android) ,[__speech translation__](https://developers.google.com/ml-kit/genai/speech-translation/android) , and[__text-to-speech__](https://developers.google.com/ml-kit/genai/text-to-speech/android) APIs on phones and smart glasses, to a[__Formula E AI co-driver__](https://youtu.be/nV63eqjPeEI?si=Uzj9_8bjHzww5sRv) built with Gemini Nano, ML Kit direct model access, and the[__Agent Development Kit (ADK)__](https://developer.android.com/ai/adk) .\n\nFor workflows that span cloud and local processing, [__Firebase AI Logic__](https://youtu.be/IPKerNnpddQ?si=1Io0uYXxpHAiSTLO) offers a straightforward hybrid solution. You can call advanced cloud models like Gemini 4 while using on-device inference with Gemini Nano when available. To protect your app and manage costs in production, use [__Firebase App Check__](https://firebase.google.com/docs/app-check), the new [__server prompt templates__](https://firebase.google.com/docs/ai-logic/server-prompt-templates/get-started), and Firebase spend caps. \n\nAs showcased in the keynote demo with Jetpacker's live booking assistant, the Jetpack Compose A2UI renderer is now available in alpha to help your agents \"speak UI\". Your agents can stream rich, interactive native Compose UIs directly from a JSON protocol. Get started with the [__A2UI Compose__](https://goo.gle/a2ui-compose-docs) renderer and give us your feedback. Watch this __talk__ to see how to implement it in your app. \n\n## Reach across Gemini and Search with Connected Apps Platform\n\nAcross Google surfaces, users are shifting from asking questions to taking action. We introduced the [__Connected Apps Platform__](https://developers.google.com/connected-apps) so you can reach high-intent users across Gemini and Search, combining Android MCP for native on-device execution with remote MCP servers for cross-platform reach. You can start building and testing locally today with [__Gemini Apps Developer Mode__](https://developers.google.com/connected-apps/mcp/dev-mode). When you're ready for production, [__join the preview waitlist__](https://goo.gle/connected-apps-interest); preview capacity is currently limited to selected production-ready apps in supported categories, with broader self-serve access coming later. \n\nTo walk you through building, testing, and publishing your first Connected App, watch Extend your app to Gemini and Search with the Connected Apps Platform.\n\n## Start building intelligent apps with the latest updates\n\nTo start building, create on-device agents with [__ML Kit agentic workflows__](https://developers.google.com/ml-kit/genai/agent/android) alongside [__direct model access__](https://developers.google.com/ml-kit/genai/prompt/android) with new Android [__skills__](https://github.com/android/skills/tree/main/device-ai).  Make sure you opt in to the [__AIcore Developer Preview program__](https://developers.google.com/ml-kit/genai/aicore-dev-preview) when testing with new capabilities in preview models. Bring intelligent features to your app with ML Kit APIs and run custom ML models with LiteRT in Google Play Services. Run Inference with Gemini models in the cloud with [__Firebase AI Logic__](https://developer.android.com/ai/gemini) directly and stream native Compose UIs from JSON using the [__Jetpack Compose A2UI renderer__](https://goo.gle/a2ui-compose-docs). Finally, integrate with the Android intelligence system, prototype with Android MCP using the AppFunctions [__skill and sample agent__](https://developer.android.com/ai/appfunctions#skills-and-samples) and sign up for the [__Connected Apps Platform developer preview__](https://goo.gle/connected-apps-interest).\n\nWe can't wait to see what you build!\n\n- \n              [Product News](https://developer.android.com/blog/categories/product-news)\n            Googlebook introduces a new category of laptops built on a shared Android foundation. High-performance hardware from partners such as HP, Dell, Lenovo, Acer, and Asus, combines mobile convenience with desktop power.\n- \n              [Product News](https://developer.android.com/blog/categories/product-news)\n            Today, the Jetpack Compose August ‘26 release is stable! [Nick Butcher](https://developer.android.com/blog/authors/nick-butcher) •\n      5 min read\n- \n              [Product News](https://developer.android.com/blog/categories/product-news)\n            With the introduction of the Pixel 11 Pro Fold, Pixel Watch 5, and the entire Pixel family, users are moving seamlessly across diverse screen sizes, unique postures, and intelligent experiences.\n\nGet the latest Android development insights delivered to your inbox weekly.", "url": "https://wpnews.pro/news/from-in-app-agents-to-the-android-intelligence-system-whats-new-in-intelligent", "canonical_source": "https://developer.android.com/blog/posts/android-intelligence-system-in-app-agents-ads", "published_at": "2026-11-05 00:00:00+00:00", "updated_at": "2026-11-05 20:56:28.816109+00:00", "lang": "en", "topics": ["ai-agents", "agent-protocols", "ai-tools", "developer-tools", "artificial-intelligence"], "entities": ["Google", "Android", "Gemini", "Gemini Nano 4", "Android MCP", "AppFunctions Jetpack library", "ML Kit GenAI APIs", "Firebase AI Logic"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/from-in-app-agents-to-the-android-intelligence-system-whats-new-in-intelligent", "markdown": "https://wpnews.pro/news/from-in-app-agents-to-the-android-intelligence-system-whats-new-in-intelligent.md", "text": "https://wpnews.pro/news/from-in-app-agents-to-the-android-intelligence-system-whats-new-in-intelligent.txt", "jsonld": "https://wpnews.pro/news/from-in-app-agents-to-the-android-intelligence-system-whats-new-in-intelligent.jsonld"}}