529 results
NOV. 20, 2026 / AI
Agent Anomaly Detection now monitors ADK agents running across AWS, Azure, or on-premises by analyzing their traces and logs in your Google Cloud project. By ingesting OpenTelemetry-formatted data through the Telemetry API, it evaluates full conversations for behavioral drift without needing access to the agent's underlying runtime. This enables security teams to detect risks like rogue behaviors, tool misuse, and resource exhaustion across multi-cloud environments.
NOV. 20, 2026 / Gemini
Semantic governance policies enable developers to govern AI agents by evaluating every proposed tool call inline before execution. Operating via Agent Gateway, the policy engine checks each action against user intent and plain-language rules to prevent unauthorized data sharing and prompt injection attacks. Developers can easily attach natural-language constraints to their agents and monitor auditable verdicts through Cloud Logging.
NOV. 17, 2026 / Mobile
Meet Another Build File Service (ABFS), Google's open-source content-addressable filesystem and build cache that cuts Android checkouts to <8s and builds to ~2m.
NOV. 17, 2026 / Web
Google AI Studio now lets developers build, test, and ship full-stack Kotlin Android apps from a single prompt—complete with Cloud Firestore, Firebase Authentication, Firebase AI Logic, a faster HD emulator with audio, visual screenshot debugging, and direct publishing to your personal Google Play library.
NOV. 17, 2026 / AI
Google's Gemini 4 Hydrogen brings strong spatial and embodied reasoning capabilities to a fast, efficient model built specifically for robotics. To help developers put these capabilities to work, the new Robotics plugin for Google Antigravity transforms the platform into a comprehensive workbench supporting rapid hardware bring-up, MuJoCo simulation, and closed-loop control. Developers can leverage these tools to transition from an unboxed robot arm to a fully functional real-to-sim-to-real application in an afternoon using natural language prompts and day-one support in the google-genai SDKs.
NOV. 16, 2026 / AI
How we eliminated floating-point train–inference logprob drift for on-policy LLM reinforcement learning across 64 Cloud TPU v5p chips using a generalizable four-part JAX and Pallas recipe in Tunix.
NOV. 11, 2026 / Mobile
A2UI 1.0 is an open protocol for generative UI that enables AI agents to render interactive, native screens across web, mobile, and desktop applications. Developers can leverage open-source renderer SDKs—including React, Angular, Lit, Flutter, SwiftUI, and Jetpack Compose—alongside agent SDKs for Python, TypeScript, and Dart. The release introduces bidirectional function calls, swappable inference formats, and secure data binding to help teams seamlessly integrate generative UI into their product stacks.
NOV. 10, 2026 / Mobile
Google AI Edge Gallery now supports on-device, offline Automatic Speech Recognition (ASR) and Text-to-Speech (TTS) capabilities for building developer-friendly voice applications. Developers can leverage ML Kit for optimized Android performance, or use MediaPipe Tasks and LiteRT for cross-platform open-weight model integration. This local pipeline seamlessly pairs lightweight speech models with on-device small language models like Gemini Nano and Gemma 4 to enable real-time streaming transcription and low-latency synthesis.
NOV. 9, 2026 / Mobile
Developers can now build applications powered by Google Maps Platform directly within Google AI Studio by prompting Gemini with real-world geospatial concepts. The integration eliminates traditional configuration hurdles by providing one-click demo keys that generate instantly without requiring Cloud Console redirects or credit cards. This setup grants developers immediate access to core APIs—including Maps, Places, and Routes—supported by daily sandbox quotas for seamless prototyping.
NOV. 9, 2026 / AI
Google Cloud's MaxText framework now supports long-context training up to 14 million tokens on Cloud TPUs by implementing four context-parallel strategies: All-gather, A2A, P2P, and USP. Powered by the Tokamax Splash Attention kernel, these strategies effectively manage attention compute and memory bottlenecks without materializing full key-value sequences in high-bandwidth memory. Developers can adopt these capabilities in MaxText v0.2.4 to achieve high Model FLOPs Utilization (MFU) across large-scale model training workflows.