Building Agents with the Gemini Interactions API

kept by eddie jan 15

Building an agent with the Gemini Interactions API requires only an LLM loop, tool definitions, and server-side state management in under 100 lines of Python.

Gemini 3 Flash: Frontier intelligence built for speed
Google announced Gemini 3 Flash, a frontier-intelligence model optimized for speed and cost, outperforming prior Pro models on key benchmarks, now available to developers.
also on Gemini 3 Flash, Google, #developer-tools
Surpassing Frontier Performance with Fusion — OpenRouter Blog
OpenRouter's Fusion, which synthesizes outputs from multiple language models via a judge model, outperformed individual frontier models including GPT-5.5 and Claude Opus 4.8 on deep research tasks, with a budget panel achieving near-frontier performance at half the cost.
also on Gemini 3 Flash, #developer-tools
Introducing FastMCP 3.0 🚀
FastMCP 3.0 introduces a composable architecture based on Components, Providers, and Transforms to build durable, production-ready MCP servers in Python.
also on #python, #ai-agents, #software-engineering, #developer-tools
Agents can't choose between structure and flexibility
The article argues that employing pure code or pure markdown to specify AI agent behavior is a failure mode, and advocates for a hybrid approach.
also on #python, #ai-agents, #developer-tools