
Building high-performance, context-aware AI apps
How do you combine the reasoning power of Large Language Models (LLMs) with the accuracy of your own enterprise data?
February 26, 2026
9:00 AM - 6:30 PM EST
550 Washington St
New York City, NY 10014
Join us for a hands-on workshop dedicated to the architecture of modern AI applications. We will dissect the RAG (Retrieval Augmented Generation) stack, showing you how to build systems that are both accurate and fast. Key takeaways include:
9:00 AM–9:30 AM EST | Guest Registration |
|---|---|
9:30 AM–9:45 AM EST | Introductions |
9:45 AM–10:45 AM EST | Overview of AlloyDB and AlloyDB AI + Natural Language |
10:45 AM–11:30 AM EST | AlloyDB Columnar Engine |
|---|---|
11:30 AM–12:30 PM EST | Lab 1 - Configuring Vector Search in AlloyDB |
12:30 PM–1:30 PM EST | Networking Lunch |
1:30 PM–3:00 PM EST | Lab 2 - Building LLM and RAG based chat applications with AlloyDB and Vertex AI |
3:00 PM–3:15 PM EST | Break |
3:15 PM–4:45 PM EST | Lab 3 - Accelerate Analytical Queries using AlloyDB Columnar Engine |
4:45 PM–5:15 PM EST | AlloyDB + AI Roadmap |
5:15 PM–6:30 PM EST | Happy Hour and Networking |