Stop building slow AI: Optimizing multi-agent systems for production

Google Cloud Tech · Beginner ·🤖 AI Agents & Automation ·3h ago
Build a Multi-Agent Marathon Planner with ADK and A2A → https://goo.gle/4nyWbRE [Demo] Race Condition → https://goo.gle/3Pbv16Z Join Casey West and Ivan Ardini as they break down the multi-agent architecture behind their Dev Keynote demo, revealing the secrets to optimizing complex AI systems for production constraints. Discover how to leverage the Agent Development Kit (ADK) to build specialized "planner," "simulator," and "evaluator" agents, and learn advanced techniques for real time evaluation using Gemini 3.1 Pro. Explore how to optimize Agent2Agent Protocol (A2A) communication using Pub/Sub, WebSockets, and protocol buffers, and master Agent-to-User Interface (A2UI) generation to build responsive, scalable frontends for cloud applications. Chapters: 0:00 - Intro 1:14 - Considerations for building the Cloud Next 2026 demo 3:42 - Agents as judges 5:20 - Tools vs skills for AI agents 7:55 - Evaluating AI agents 11:33 - Using Agent2Agent Protocol (A2A) in the demo 16:20 - How can developers trust the output of AI models? 18:41 - Data governance for multi-agent systems 19:50 - Getting started with codelabs Watch more Google Cloud Next 2026 → https://goo.gle/next-talks-2026 🔔 Subscribe to Google Cloud Tech → https://goo.gle/GoogleCloudTech #GoogleCloudNext Speakers: Casey West, Ivan Nardini Products Mentioned: Agent Development Kit, Gemini, Agent2Agent Protocol, Pub/Sub, WebSockets, Agent-to-User Interface, Gemini Enterprise Agent Platform
Watch on YouTube ↗ (saves to browser)
Sign in to unlock AI tutor explanation · ⚡30

Related AI Lessons

"The Bug That Forced Us to Add Agent Memory"
Learn how a bug led to the development of an agent memory system in the Nexus Core AI OS project, highlighting the importance of persistent memory in AI systems
Dev.to AI
35 ChatGPT Prompts for Talent Acquisition Specialists: Source Smarter, Screen Faster, and Hire Better
Use AI-powered ChatGPT prompts to streamline talent acquisition processes and improve hiring outcomes
Dev.to AI
Armorer v0.1.19: building the local ops layer for AI agents
Learn how Armorer v0.1.19 simplifies local operations for AI agents, streamlining installation, configuration, and management
Dev.to AI
Meta Crashed My Server to Train Their Ai. 110 People Said It Happened to Them Too.
Meta's AI training caused a server crash for one developer, with 110 others reporting similar experiences, highlighting the potential risks of AI development on external infrastructure
Medium · Startup

Chapters (9)

Intro
1:14 Considerations for building the Cloud Next 2026 demo
3:42 Agents as judges
5:20 Tools vs skills for AI agents
7:55 Evaluating AI agents
11:33 Using Agent2Agent Protocol (A2A) in the demo
16:20 How can developers trust the output of AI models?
18:41 Data governance for multi-agent systems
19:50 Getting started with codelabs
Up next
How AI is Changing DevOps Engineering | Ex-Amazon Engineer reveals the secret | TrainWithShubham
GeeksforGeeks
Watch →