Deep dive: Delivering and managing an LLM Agent application with KusionStack

+++ Fully booked - no more seats available +++ Deep dive into the intricacies of KusionStack and learn how to deploy, update, and manage LLM Agent applications on Kubernetes and cloud resources using KusionStack. Get to know the philosophies, methodologies, and stories behind its evolution and how it solves problems.
June 11
03:00 PM
08:00 AM
Forest Chen
Senior Software Engineer at Ant Group
Dayuan Li
Senior Software Engineer, AntGroup
Ke Wu
Staff Software Engineer from the Platform Engineering Team, Ant Group
*Sponsored by

+++ Fully booked - no more seats available +++

This workshop serves as an in-depth exploration of KusionStack and how it can be leveraged to deploy an LLM Agent application to the cloud. The demo consists of several stages that progressively carry out a story to deploy and manage an LLM Agent, each slightly more complex than the last. 

This session is designed to provide a practical understanding of managing complex applications in modern cloud-native environments. Through real-world examples, we'll demonstrate KusionStack’s pivotal role in enabling the realization from intents to actual deliveries, providing actionable insights for leveraging KusionStack in a similar environment.


- A Kubernetes cluster. Minikube or Kind is fine too

- AWS Account with AccessKey and SecretKey ready (Optional, for provisioning cloud resources)

- An OpenAI key (Optional, for testing the Agent Application)