DUMMY TEXT
For upcoming STACK webinars and a full list of our past events, please visit our Meetup page.
Overview
How do we scale AI agents from individual prototypes to enterprise-wide systems? This session breaks down the two critical layers of a scalable agentic architecture: The Execution Layer, which provides a standardised platform for agent runtime scaling, and the Orchestration Layer, which leverages event-driven architecture to keep agents reactive and synchronised.
Explore the transition from solo AI-assisted development to a centralised platform model that translates individual productivity gains into aggregate organisational benefits. This involves building runtimes for a multi-assistant era, where governance is a feature rather than an operational tax. Complementing this, we’ll examine how event-driven architecture acts as a backbone to update knowledge bases in real-time with high-quality data. Learn how this approach simplifies the incorporation of new agents, allowing you to scale from single-agent to multi-agent applications without increasing operational load or compromising data governance.
This session concludes with a community discussion designed for practitioners to exchange shared challenges, and learn from each other’s experiences in building robust AI systems. We’d like to hear from your experiences too!
Who should attend: AI engineers, platform architects, and data practitioners focused on transitioning AI agents from experimental scripts into resilient and production-ready enterprise systems.
Programme rundown
6:30pm – Networking
7:00pm – Introduction by STACK Community
7:05pm – Opening
7:15pm – Scaling AI Development
By Ng Shangru, Staff Software Engineer, AI Programme, GovTech Singapore
7:35pm - From Demo to Production: Scaling Agentic AI with Event-Driven Architecture Seamlessly
By Shelvia Hotama, Senior Solutions Engineer, Confluent
7:55pm - Discussion on Building Robust and Scalable AI Systems with Shangru and Shelvia
8:15pm - Q&A
8:30pm - End of STACK Meetup
Last updated 04 May 2026
Thanks for letting us know that this page is useful for you!
If you've got a moment, please tell us what we did right so that we can do more of it.
Did this page help you? - No
Thanks for letting us know that this page still needs work to be done.
If you've got a moment, please tell us how we can make this page better.