264001
eyJ0eXAiOiJKV1QiLCJhbGciOiJIUzI1NiJ9.eyJpc3MiOiJid2V2ZW50cy1wdWJsaWMtYXBpIiwiYXVkIjpbInB1YmxpYy13ZWIiXSwic3ViIjoiaHR0cHM6Ly93d3cuZ29vZ2xlY2xvdWRldmVudHMuY29tIiwiaWF0IjoxNzc1ODk5NTIxLCJuYmYiOjE3NzU4OTk1MjEsImV4cCI6MTc3NTkwMzEyMSwiY29udGV4dCI6eyJwYXlsb2FkIjp7ImlkIjoiIiwicmVnVHlwZU5hbWUiOiIiLCJldmVudF9pZCI6IjI2NDAwMSIsImNfMzI5MDQxNiI6IiJ9fX0.lqMgx5T6lsKsgRInpcS0nlBtd50H9u9aVam2yPr5iBk
phase 5 session info modal
Day 3 – April 24, 2026
Breakouts
BRK2-128 • Kubernetes, Cloud Runtimes • Technical
How GKE builds itself with AI
location_on Jasmine A
schedule 8:30 AM - 9:15 AM
Building the future of Google Kubernetes Engine (GKE) requires architecting the same agentic workflows we provide to our customers. Join this session to explore the internal architecture that underpins our solution for complex feature discovery, which uses proactive, autonomous agents. Discover how we build and scale these discovery agents on GKE, integrating real-time feedback loops and kernel-level isolation. We’ll deconstruct this GKE-on-GKE pattern, providing battle-tested insights for your own agentic infrastructure on Google Cloud. Leave with a reference architecture and blueprint for building your own autonomous, self-optimizing platforms. Read more
This agenda widget contains logic for handling same sessions available at multiple times
GTM Tracking Header name present
Session
contains logic for gtm tracking when modal open