All videos
0:00 / 0:00
research

AI Dev 26 x SF | Luke Kim: The Agent Data Stack—Why Every AI Agent Needs Its Own Data Stack

DeepLearning.AI16 June 2026Watch on YouTube

What you'll learn

  • AI agents require their own decentralized data stacks instead of centralized platforms for enhanced security and sandboxing
  • Real-time data is essential for AI agents to function reliably
  • The architectural shift from centralized to distributed requires specific patterns and modern data infrastructure

Frequently asked questions

Why does every AI agent need its own data stack?
Each AI agent needs its own decentralized data stack for security, sandboxing and to provide reliable real-time data access. This is preferable to centralized data and AI platforms that all agents depend on.
What is the difference between the old and new approach for AI agents?
In the old world, organizations relied on one centralized data and AI platform. In the new world, AI agents each need their own sandboxed, secure and modern data stack for better independence.
What key elements are needed for distributed data stacks?
The architectural shift from centralized to distributed requires specific patterns and modern data infrastructure. Luke Kim demonstrates live how these architectural patterns work in practice.

Topics

ai agentsdata infrastructurearchitecturereal-time data

In this video

StacksStacks

Read next

Description from the channel

From centralized to distributed: In the old world, organizations relied on one centralized data and AI platform. In the new world of AI agents, every agent needs its own sandboxed, secure, and modern data stack. In this 20-minute talk with live demo by Spice AI's Luke Kim, he explores why this architectural shift is critical and the key patterns required to give agents reliable, real-time data.