Build a multi-agent system using ADK & MCP @googlecloudtech

Uploaded June 2026 | Updated September 2026, 2 weeks ago

Join Gemini Enterprise Agent Ready (GEAR) for the latest agent resources here. → https://goo.gle/3Srblgl

Learn how to build a production-grade agent with Google's Agent Development Kit (ADK), the Model Context Protocol (MCP), and Gemini 3 Flash. Google Developer Expert, Jigyasa Grover showcases “Critics Cut,” a multilingual, context-aware AI assistant designed to eliminate the endless scrolling when looking for something to watch.

Speakers: Jigyasa Grover
Products Mentioned: Agent Development Kit, Model Context Protocol

Build a multi-agent system using ADK & MCP

How to build a continuous evaluation pipeline for multi-agent systems with Gemini

How we built 1,000 AI agents that run a marathon

Full-stack Dart is here: Top 5 Flutter highlights from Cloud Next 26

Workflow agents and communication in ADK

How to vibe code securely (without getting hacked)

Whats new for AI on GKE: Training, serving, and agents

$Next gen agentic architecture: Hands on with Gemini 3.5 & ADK In this interview from Google I/O, Dave Elliot, Katie Nguyen and Lavi, break down the monumental releases of Gemini 3.5 and Gemini Omni. Discover how the Gemini Enterprise Agent Platform optimizes the end to end lifecycle, from initial scaffolding with the Agent Development Kit (ADK) and Antigravity CLI, to scaling, governance, and automated evaluations. Watch the demonstrations of Gemini 3.5 Flash delivering near state of the art coding and tool calling performance at a fraction of the cost, alongside mind bending any to any multi-modal video generation capabilities that are redefining localized edge automation and agentic workflows. Watch more Google I/O Interviews → https://goo.gle/io-tech-chats 🔔 Subscribe to Google Cloud Tech → https://goo.gle/GoogleCloudTech #GoogleIO #GoogleCloud Speakers: Dave Elliot, Lavi Nigam, Katie Nguyen Products Mentioned: Gemini, Gemini Enterprise Agent Platform, Agent Development Kit, Antigravity CLI$

NoSQL for modern apps and AI: The future of Memorystore, Firestore, and Bigtable