Observed Signal · Sep 28, 2026 · Technical Release · Source: Android Developers Blog · Impact: 4/5 · Sentiment: Positive
Google Android Build In-App Agentic Workflows
Google's Android Developers Blog has published a technical guide on building in-app agentic workflows for Android apps, using cloud-hosted backends. The post introduces the Agent Development Kit (ADK), along with two protocols: AG-UI for standardizing agent-client communication and A2UI for dynamically describing UI components. Developers can use these to create autonomous multi-agent systems, such as a Booking Assistant in the Jetpacker sample app, that handle complex tasks like booking flights and hotels. The backend agents run autonomously, while the Android client renders interactive UI via Jetpack Compose using the new androidx.a2ui libraries.
Technical release from Google for building agentic AI workflows in Android apps; relevant for AdTech ecosystem as it enables in-app AI-driven interactions and UI rendering, potentially impacting mobile advertising and app monetization.
MARKET SIGNALS
Track Google Signals & Strategic Shifts
Polaris7 connects regulatory filings, primary sources, leadership changes, and M&A activity into structured intelligence. Set up your Polaris7 workspace to monitor relevant companies in your executive briefing.
- Verified primary sources
- Automated briefings
- Instant watchlist setup
Key Takeaways & Evidence Grounding
- Google released a technical blog post on in-app agentic workflows for Android.
- The post introduces the Agent Development Kit (ADK) for building multi-agent systems.
- It standardizes agent-client communication with AG-UI and dynamic UI rendering with A2UI.
- New Jetpack Compose libraries (androidx.a2ui) facilitate native rendering of agent-driven UI.
- The Jetpacker sample app demonstrates a Booking Assistant coordinating flights, hotels, and restaurants.
Connected Companies & Entities
“Google's Android Developers Blog has published a technical guide on building in-app agentic workflows for Android apps.”
Ontology Mapping & Concepts
Related Market Signals & Shifts
Recent verified developments and strategic activity across this market segment.
Android unveils in-app agents, Android MCP, A2UI for connected apps
At the Android Developer Summit, Google announced new developer tools and APIs for building intelligent, agentic experiences in Android apps. Key announcements include Android MCP, a unified tool-calling framework powered by the AppFunctions Jetpack library, enabling apps to connect with AI agents like Gemini. The Connected Apps Platform preview program lets apps reach users across Gemini and Search. Other updates include ML Kit GenAI APIs with new Agentic API for on-device agent workflows, LiteRT in Google Play services for smaller APKs and faster GPU inference, and the alpha release of the A2UI Compose renderer for streaming native Compose UIs from JSON. These tools aim to help developers create apps that can complete multi-step tasks on behalf of users.
Android Dev Summit: New Agentic Tools and XR Launch
At the Android Dev Summit, Google announced the broad availability of new tools and APIs for Android development, focusing on agentic experiences and flexibility. Key updates include Android Studio Rabbit 2, which supports bring-your-own-agent (BYOA) with compatibility for over 40 ACP-compliant agents like Claude Agent and Codex. Android CLI now offers device streaming, Compose previews, profiling, and app analysis features. New Android skills and plugins for Antigravity, Claude Code, and Codex were also launched. Additionally, Google introduced the Connected Apps Platform to integrate app services with Gemini and Search, and new APIs like AppFunctions, A2UI, and ML Kit's Agentic API. For form factors, AppState is now in alpha, Navigation 3 1.2 is stable, and Compose 1.13 will bring adaptive layouts. In collaboration with XREAL, Google launched XREAL AURA, the first wired XR glasses powered by Android XR, and made core Jetpack XR SDK libraries and emulators stable.
Google ADK Architecture and Core Components
This article presents a high-level architecture and component breakdown for the Google Agent Development Kit (ADK), a framework for building, testing, and deploying AI agent applications. It describes layered architecture including user interfaces, an ADK Runtime & Runner, an agent system (LLM agents, workflows, custom agents), foundational components (session, state, memory, events, tools, artifacts), and a models & knowledge layer that integrates Gemini-family models via Vertex AI or Google AI Studio and supports Retrieval-Augmented Generation (RAG). The piece also covers observability and governance (traceability, logs, metrics, evaluation, alerts, security) and deployment options such as a managed Agent Runtime on Google Cloud, Cloud Run, GKE, and on-premises environments.
WATCHLIST & BRIEFINGS
Receive future signals for Google & competitors in your briefing
Stay ahead of material M&A deals, leadership changes, account wins, and product rollouts. Polaris7 connects primary filings, company newsrooms, and trade reporting directly into your executive briefing.
- Regular primary-source checks
- Structured Watchlist briefings
- Preserves current context
Market Signal Monitoring
Follow affected companies in Polaris7 with regular source checks and structured Watchlist briefings.
Monitor Google
Follow affected companies in Polaris7 with regular source checks and structured Watchlist briefings.
