How to build and scale multi-agent AI systems on GKE
Google kubernetes engine Gke Multi Agent ai Agentic ai Kubernetes Gemini Model context protocol Mcp server Bigquery Property graph Gql Knowledge graph Cloud storage Data pipeline Platform engineering Infrastructure automation
This advanced tutorial demonstrates how to build and scale multi-agent AI systems on Google Kubernetes Engine, covering Agent Sandbox deployment for automated evaluation, Gemini-powered troubleshooting via MCP server for infrastructure diagnostics, and building distributed knowledge acquisition pipelines using Gemini 3.5 Flash that store entity relationships in BigQuery Property Graphs with GQL queries. Designed for platform engineers and ML ops professionals seeking to operationalize agentic AI workloads at scale.
Related videos
The future of Cloud AI: Mastering MCP servers, Gemini, and agentic workflows
Automate Google Cloud with Cloud CLI Remote MCP Server
Data agent kit: Your coding agent can now query your data
Don't Start With 500 Clusters: Patterns in Scaling Multi-Cluster Kubernetes… N. Bora & M. Morrison
What's new for AI on GKE: Training, serving, and agents
Automate SAP order-to-cash with multi-agent AI & Google Agent Development Kit (ADK)
Automate project intake with multi-agent AI using MCP, Google ADK, Cloud Run, and BigQuery
Building production ready full stack apps with AI
Keynote: The Future of Cloud Native Is… Agentic - Lin Sun, Head of Open Source, Solo.io (ASL)
Sponsored Keynote: From Complexity to Clarity: Engineering an Invisible Kubernetes - J. Butler (ASL)
Orchestrating ML/AI workloads with TPUs on GKE
