https://developers.googleblog.com/rss/Updates on changes and additions to the Google Developers Blog.en-usSat, 31 Jan 2026 15:25:04 +0000https://developers.googleblog.com/beyond-the-chatbot-a-blueprint-for-trustable-ai/At Thunderhill Raceway Park, a team of Google Developer Experts (GDEs) put a new "Trustable AI Framework" to the test. Here is how they used GCP, Gemini and Antigravity to turn high-velocity racing into a masterclass for agentic architecture.https://developers.googleblog.com/beyond-the-chatbot-a-blueprint-for-trustable-ai/https://developers.googleblog.com/tailor-gemini-cli-to-your-workflow-with-hooks/New Gemini CLI hooks (v0.26.0+) let you tailor the agentic loop. Add context, enforce policies, and block secrets with custom scripts that run at predefined points in your workflow.https://developers.googleblog.com/tailor-gemini-cli-to-your-workflow-with-hooks/https://developers.googleblog.com/litert-the-universal-framework-for-on-device-ai/LiteRT, the evolution of TFLite, is now the universal framework for on-device AI. It delivers up to 1.4x faster GPU, new NPU support, and streamlined GenAI deployment for models like Gemma.https://developers.googleblog.com/litert-the-universal-framework-for-on-device-ai/https://developers.googleblog.com/a-guide-to-fine-tuning-functiongemma/FunctionGemma is a specialized AI model for function calling. This post explains why fine-tuning is key to resolving tool selection ambiguity (e.g., internal vs. Google search) and achieving ultra-specialization, transforming it into a strict, enterprise-compliant agent. A case study demonstrates the improved logic. It also introduces the "FunctionGemma Tuning Lab," a no-code demo on Hugging Face Spaces, which streamlines the entire fine-tuning process for developers.https://developers.googleblog.com/a-guide-to-fine-tuning-functiongemma/https://developers.googleblog.com/under-the-hood-universal-commerce-protocol-ucp/The Universal Commerce Protocol (UCP) is a new, open-source standard for agentic commerce, co-developed by Google and industry leaders. It establishes a common, secure language to connect consumer surfaces (like Gemini and AI Mode in Search) with business backends, enabling seamless shopping from product discovery to purchase. UCP simplifies integration for businesses, supports various payment providers, and is designed to power the next generation of conversational commerce experiences.https://developers.googleblog.com/under-the-hood-universal-commerce-protocol-ucp/https://developers.googleblog.com/a-developers-guide-to-debugging-jax-on-cloud-tpus-essential-tools-and-techniques/A practical guide to debugging and profiling JAX on Cloud TPUs. It outlines core components (libtpu, JAX/jaxlib) and essential techniques. Tools covered include: Verbose Logging (via libtpu env vars), TPU Monitoring Library for performance metrics, tpu-info for real-time utilization, XLA HLO Dumps for compiler debugging, and the XProf suite for in-depth performance analysis.https://developers.googleblog.com/a-developers-guide-to-debugging-jax-on-cloud-tpus-essential-tools-and-techniques/https://developers.googleblog.com/real-world-agent-examples-with-gemini-3/Gemini 3 is powering the next generation of reliable, production-ready AI agents. This post highlights 6 open-source framework collaborations (ADK, Agno, Browser Use, Eigent, Letta, mem0), demonstrating practical agentic workflows for tasks like deep search, multi-agent systems, browser and enterprise automation, and stateful agents with advanced memory. Clone the examples and start building today.https://developers.googleblog.com/real-world-agent-examples-with-gemini-3/https://developers.googleblog.com/gemini-3-flash-is-now-available-in-gemini-cli/Gemini 3 Flash is now available in Gemini CLI. It delivers Pro-grade coding performance with low latency and a lower cost, matching Gemini 3 Pro's SWE-bench Verified score of 76%. It significantly outperforms 2.5 Pro, improving auto-routing and agentic coding. It's ideal for high-frequency development tasks, handling complex code generation, large context windows (like processing 1,000 comment pull requests), and generating load-testing scripts quickly and reliably.https://developers.googleblog.com/gemini-3-flash-is-now-available-in-gemini-cli/https://developers.googleblog.com/conductor-introducing-context-driven-development-for-gemini-cli/Conductor is a new Gemini CLI extension that promotes context-driven development. It shifts project context from chat logs to persistent Markdown files for formal specs and plans, ensuring AI agents adhere to project goals, style, and tech stack. This structured workflow is great for "brownfield" projects and teams, allowing for safe iteration and consistent code contributions while keeping the human developer in control.https://developers.googleblog.com/conductor-introducing-context-driven-development-for-gemini-cli/https://developers.googleblog.com/introducing-agent-development-kit-for-typescript-build-ai-agents-with-the-power-of-a-code-first-approach/Introducing the Agent Development Kit (ADK) for TypeScript, an open-source framework for building complex, multi-agent AI systems with a code-first approach. Developers can define agent logic in TypeScript, applying traditional software development best practices (version control, testing). ADK offers end-to-end type safety, modularity, and deployment-agnostic functionality, leveraging the familiar TypeScript/JavaScript ecosystem.https://developers.googleblog.com/introducing-agent-development-kit-for-typescript-build-ai-agents-with-the-power-of-a-code-first-approach/https://developers.googleblog.com/developers-guide-to-multi-agent-patterns-in-adk/Learn how to build modular and reliable agentic applications using 8 effective multi-agent design patterns with the Agent Development Kit (ADK).https://developers.googleblog.com/developers-guide-to-multi-agent-patterns-in-adk/https://developers.googleblog.com/introducing-a2ui-an-open-project-for-agent-driven-interfaces/A2UI is an open-source project for agent-driven, cross-platform, and generative UI. It provides a secure, declarative data format for agents to compose bespoke interfaces from a trusted component catalog, allowing for native styling and incremental updates. Designed for the multi-agent mesh (A2A), it offers a framework-agnostic solution to safely render remote agent UIs, with integrations in AG UI, Flutter's GenUI SDK, Opal, and Gemini Enterprise.https://developers.googleblog.com/introducing-a2ui-an-open-project-for-agent-driven-interfaces/https://developers.googleblog.com/building-agents-with-the-adk-and-the-new-interactions-api/The new Gemini Interactions API enables stateful, multi-turn AI agent workflows, providing a single interface for raw models and the Gemini Deep Research Agent. It can be integrated with existing ADK systems as a superior inference engine with simplified state management, or used as a transparent remote A2A agent via InteractionsApiTransport, allowing seamless expansion of multi-agent systems with minimal refactoring.https://developers.googleblog.com/building-agents-with-the-adk-and-the-new-interactions-api/https://developers.googleblog.com/pick-up-exactly-where-you-left-off-with-session-management-in-gemini-cli/Gemini CLI's new automatic **Session Management** (v0.20.0+) saves your conversation history, tool outputs, and reasoning, providing project-specific context. Resume easily using the **Interactive Session Browser** (`/resume`) or command-line flags (`--resume`). This feature ensures you never lose your work state, capturing prompts, tool execution details, and usage stats. Customize history with cleanup policies in `settings.json`.https://developers.googleblog.com/pick-up-exactly-where-you-left-off-with-session-management-in-gemini-cli/https://developers.googleblog.com/dont-trust-verify-building-end-to-end-confidential-applications-on-google-cloud/Google Cloud enables end-to-end confidential applications, protecting sensitive data 'in-use' with hardware isolation. The solution combines Confidential Space (TEE/attestation), Oak Functions (private sandbox), and Oak Session (attested end-to-end encryption for scale). This framework anchors user trust in open-source components, proving confidentiality for sensitive workloads like proprietary GenAI models, even when running behind untrusted load balancers.https://developers.googleblog.com/dont-trust-verify-building-end-to-end-confidential-applications-on-google-cloud/https://developers.googleblog.com/mediatek-npu-and-litert-powering-the-next-generation-of-on-device-ai/LiteRT and MediaTek are announcing the new LiteRT NeuroPilot Accelerator. This is a ground-up successor for the TFLite NeuroPilot delegate, bringing seamless deployment experience, state-of-the-art LLM support, and advanced performance to millions of devices worldwide.https://developers.googleblog.com/mediatek-npu-and-litert-powering-the-next-generation-of-on-device-ai/https://developers.googleblog.com/architecting-efficient-context-aware-multi-agent-framework-for-production/ADK introduces **Context Engineering** to scale AI agents beyond large context windows. It treats context as a compiled view over a tiered, stateful system (**Session, Memory, Artifacts**). This architecture uses explicit processors for transformation, enables efficient compaction and caching, and allows for strict, scoped context handoffs in multi-agent workflows to ensure reliability and cost-effectiveness in production.https://developers.googleblog.com/architecting-efficient-context-aware-multi-agent-framework-for-production/https://developers.googleblog.com/announcing-the-data-commons-gemini-cli-extension/The new Data Commons extension for the Gemini CLI makes accessing public data easier. It allows users to ask complex, natural-language questions to query Data Commons' public datasets, grounding LLM responses in authoritative sources to reduce AI hallucinations. Data Commons is an organized library of public data from sources like the UN and World Bank. The extension enables instant data analysis, exploration, and integration with other data-related extensions.https://developers.googleblog.com/announcing-the-data-commons-gemini-cli-extension/https://developers.googleblog.com/new-gemini-api-updates-for-gemini-3/Gemini 3 is available via API with updates for developers: new `thinking_level` for depth control, `media_resolution` for multimodal processing, and enforced `Thought Signatures` for agentic workflows, especially with function calling and image generation. It also introduces combining Google Search/URL Grounding with Structured Outputs and new usage-based pricing for Grounding. Best practices, like using default temperature, are advised for optimal results.https://developers.googleblog.com/new-gemini-api-updates-for-gemini-3/https://developers.googleblog.com/unlocking-peak-performance-on-qualcomm-npu-with-litert/LiteRT's new Qualcomm AI Engine Direct (QNN) Accelerator unlocks dedicated NPU power for on-device GenAI on Android. It offers a unified mobile deployment workflow, SOTA performance (up to 100x speedup over CPU), and full model delegation. This enables smooth, real-time AI experiences, with FastVLM-0.5B achieving over 11,000 tokens/sec prefill on Snapdragon 8 Elite Gen 5 NPU.https://developers.googleblog.com/unlocking-peak-performance-on-qualcomm-npu-with-litert/