AI/ML Specialist, Customer Engineer @GoogleCloud_jp . 趣味はテニスと囲碁. ex-NRI ※個人の発言であり、所属する組織を代表するものではありません。My tweets are my own and not the views of my employer.
This week, Vertex AI introduced Agent Designer in Agent Builder.
It's a low-code visual interface that allows you to orchestrate agents and subagents on a canvas, then export the logic directly to the Agent Development Kit (ADK) for code-level refinement.
> Visual Design: Create agents and logic visually.
> Playground: A chat interface to test agentic flow
> Code Transition: "Get code" lets you move from UI to Python IDE easily.
> Built-In Tools: Includes Google Search, URL context, and Vertex AI Search (RAG).
> MCP: Experimental connection to Model Context Protocol servers.
The designer is in preview with limits in MCP auth support and no advanced ADK patterns, but its visual-to-code workflow and potential platform integration are promising!
Docs: https://t.co/BkeFSw1c3Z
Introducing Nano Banana Pro (Gemini 3 Pro Image), our new state-of-the-art image generation and editing model from @GoogleDeepMind. It improves on the original model while adding new advanced capabilities, enhanced world knowledge and text rendering, allowing you to create and edit studio-quality, production-ready visuals.
We wrote a Gemini 3 Developer Guide including all new API features, Migration strategies, and technical details for building with Gemini 3 Pro preview:
- Control reasoning via `thinking_level` low and high modes.
- per part `media_resolution` for better multimodal reasoning
- Preserve reasoning context with mandatory Thought Signatures.
- Combine Structured Outputs with built-in tools like Google Search.
Meet Google Antigravity, your new agentic development platform.
An evolution of the IDE, it's built to help you:
- Orchestrate agents operating at a higher, task-oriented level
- Run parallel tasks with agents across workspaces
- Build anything with Gemini 3 Pro.