Building AI Agents with Google Gemini 3 and Open Source Frameworks- Google Developers Blog

What this post added

Introduces Gemini 3 Pro Preview, highlighting new agentic features: `thinking_level` for adjustable reasoning depth, stateful tool use via "Thought Signatures" for retaining internal reasoning, and adjustable `media_resolution` for multimodal fidelity. Details Day 0 support from open-source frameworks (LangChain, AI SDK by Vercel, LlamaIndex, Pydantic AI, n8n) for building agents with Gemini 3. Provides best practices for migrating to Gemini 3, including prompt simplification, keeping temperature at 1.0, handling thought signatures, and optimizing visual tokens.