38 results
NOV. 25, 2025 / AI
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.
NOV. 19, 2025 / AI
Gemini 3 Pro Preview is introduced as a powerful, agentic model for complex, (semi)-autonomous workflows. New agentic features include `thinking_level` for reasoning control, Stateful Tool Use via Thought Signatures, and `media_resolution` for multimodal fidelity. It has Day 0 support for open-source frameworks like LangChain, AI SDK, LlamaIndex, Pydantic AI, and n8n. Best practices include simplifying prompts and keeping temperature at 1.0.
NOV. 13, 2025 / AI
Metrax is a high-performance JAX-based metrics library developed by Google. It standardizes model evaluation by offering robust, efficient metrics for classification, NLP, and vision, eliminating manual re-implementation after migrating from TensorFlow. Key strengths include parallel computation of "at K" metrics (e.g., PrecisionAtK) for multiple K values and strong integration with the JAX AI Stack, leveraging JAX's performance features. It is open-source on GitHub.
OCT. 30, 2025 / AI
The blog post argues the request-response model fails for advanced multi-agent AI. It advocates for a real-time bidirectional streaming architecture, implemented by the Agent Development Kit (ADK). This streaming model enables true concurrency, natural interruptibility, and unified multimodal processing. ADK's core features are real-time I/O management, stateful sessions for agent handoffs, and streaming-native tools.
SEPT. 25, 2025 / AI
Gemini Robotics-ER 1.5, now available to developers, is a state-of-the-art embodied reasoning model for robots. It excels in visual, spatial understanding, task planning, and progress estimation, allowing robots to perform complex, multi-step tasks.
AUG. 28, 2025 / AI
Detailed prompting techniques and best practices for various applications, including photorealistic scenes, stylized illustrations, product mockups, and more using Google's newly released Gemini 2.5 Flash Image; a natively multimodal model capable of generating, editing, and composing images using text, supporting capabilities like text-to-image, image editing, style transfer, and multi-image composition.
AUG. 27, 2025 / Google Labs
Stax, an experimental developer tool, addresses the insufficient nature of "vibe testing" LLMs by streamlining the LLM evaluation lifecycle, allowing users to rigorously test their AI stack and make data-driven decisions through human labeling and scalable LLM-as-a-judge auto-raters.
JULY 21, 2025 / Gemini
Gemini's advanced capability for conversational image segmentation allows intuitive interaction with visual data by understanding complex phrases, conditional logic, and abstract concepts, streamlining developer experience and opening doors for new applications in media editing, safety monitoring, and damage assessment.
JULY 16, 2025 / Gemini
The updated Agent Development Kit (ADK) simplifies and accelerates the process of building AI agents by providing the CLI with a deep, cost-effective understanding of the ADK framework, allowing developers to quickly ideate, generate, test, and improve functional agents through conversational prompts, eliminating friction and keeping them in a productive "flow" state.
JULY 14, 2025 / Cloud
The Apigee API hub and Developer Portals are distinct but interconnected parts of the Apigee platform that help organizations discover and manage APIs for different personas, unlocking API potential and accelerating innovation.
