Managed Agents in the Gemini API

Google for Developers · Intermediate ·🤖 AI Agents & Automation ·1mo ago

Skills: Agent Foundations90%

Key Takeaways

Covers managed agents in the Gemini API, including the Interactions API, agent-first data model, agent-native documentation, and skills, with a live demo of a managed agent running in a remote Linux sandbox

Original Description

Logan Kilpatrick sits down with Ali Çevik and Philipp Schmid to walk through managed agents in the Gemini API. One API call, one autonomous agent running in a remote Linux sandbox, powered by Gemini 3.5 Flash and the Antigravity Agent Harness. They cover how the Interactions API works, why the data model is agent-first, the new agent-native documentation and skills, and a live demo of a managed agent turning Hacker News threads into a three-minute radio show with Lyria, Gemini TTS, and Nano Banana. Subscribe to Google for Developers → https://goo.gle/developers Speaker: Logan Kilpatrick, Ali Çevik, Philipp Schmid Products Mentioned: Google AI, Gemini

Watch on YouTube ↗ (saves to browser)

Sign in to unlock AI tutor explanation · ⚡30

More on: Agent Foundations

View skill →

Build and Deploy an Agent with Reasoning Engine in Vertex AI

Adding a Phone Gateway to a Virtual Agent

From Zero to Working AI Agent in 60 Seconds

From Zero to Working AI Agent in 60 Seconds

Create An AI Agent With Replit That Automates Your Sales

Create An AI Agent With Replit That Automates Your Sales

Capstone: Autonomous Runway Detection for IoT

Capstone: Autonomous Runway Detection for IoT

AI Agents with Model Context Protocol & Typescript

AI Agents with Model Context Protocol & Typescript

Related Reads

Beyond the Vibe Check: Why Testing AI Agents Is a Distributed Systems Problem

Testing AI agents requires Distributed Systems Engineering to ensure reliability and observability in production environments

Beyond the Vibe Check: Why Testing AI Agents Is a Distributed Systems Problem

Testing AI agents requires Distributed Systems Engineering to ensure reliability and observability in production environments

Medium · Machine Learning

Beyond the Vibe Check: Why Testing AI Agents Is a Distributed Systems Problem

Testing AI agents requires Distributed Systems Engineering to ensure reliability and observability in production environments

Etiket Tabanlı Agentic Workflow: Workflow Engine Olmadan Otonom Yazılım Pipeline’ı Kurmak

Learn to create autonomous software pipelines using existing issue tracking systems like GitHub, GitLab, or Jira without a workflow engine

Building the future of agentic infrastructure