Why Agentic AI Demands a Completely Different Network

0:32

Agentic AI isn't just another inference problem—it's a flow of compute, storage, memory, and networking that demands a fundamentally new architecture. Here's why Scale-In changes everything.

Indexed Metadata

SEO / AIO

TypeYouTube Clip

Duration33s

Transcript75 words

Sources1

Qualityacceptable

YouTube Clip

Manifest JSON Transcript TXT

Source Context

NVIDIA's Gilad Shainer Unpacks the Future of AI Networking

Create your own short

Generate a short with captions, transcript metadata, and a public video page when you choose to share it.

Create from a prompt, source, or feed

Attach transcript and manifest data

Publish or keep private

Statuscompleted

CreatedSep 28, 2026

Transcript

75 words

So what is it about agentic AI that necessitates a new type of network that you're calling Scale-In? Yeah, so first, agentic AI, it's probably the most complex workload ever created. You know, when we look on an agent, agent is not just one inference call. There is many inference calls. It's not an inquiry. There is a flow of operations. and a flow of operation that includes compute and storage and memory and networking.

Discover Pricing Login

Product

Solutions

Resources

Earn

Tools

Legal