Loading video...

Video Failed to Load

Go Home

This is the best 1 hour on graph engineering ever recorded, just released by Google how to go from a single agent to a full 24/7 system from scratch: 00:00 - what graphs actually are 09:16 - your first working agent 21:15 - graph engineering explained 41:03 - graph...

113,987 views • 2 days ago •via X (Twitter)

17 Comments

Agent Rails's profile picture
Agent Rails2 days ago

Graphs click once you have a step that can fail halfway. Single agents hide state in the prompt; a graph makes you name the node that retries and the one that must not run twice. That's most

Ben Ellsworth's profile picture
Ben Ellsworth2 days ago

How does the verifier step avoid inheriting the same blind spots as the worker agents if it is running on the same base model

Internet Labs's profile picture
Internet Labs2 days ago

The entire Twitter cohort selling $500 "Agent Masterclass" courses just got their whole business model open-sourced by Google in 60 minutes.

Hootan HT's profile picture
Hootan HT1 day ago

FYI @AmirNapster @KuomarsRahimi

AI Mastery Guide's profile picture
AI Mastery Guide2 days ago

Full hour, worth the watch

PJ / .null.'s profile picture
PJ / .null.2 days ago

you do $500 courses?

DEV's profile picture
DEV1 day ago

Building from scratch is key. Most miss the nuances in the early stages.

David Starmac Ai's profile picture
David Starmac Ai2 days ago

Bookmarking this — the jump from one agent to a system that runs 24/7 is where most people get stuck, and the graph engineering framing looks like a solid mental model for it.

Emma Rodriguez's profile picture
Emma Rodriguez1 day ago

$500 courses can't even touch this

Zhenia Vasiliev's profile picture
Zhenia Vasiliev2 days ago

Where it headed is likely Alan Kay's OOP messaging + functional programming actor model where the state is pass around. Any thoughts?

LEX's profile picture
LEX1 day ago

In 2004 Jeffrey Dean and Sanjay Ghemawat published MapReduce at Google. Twenty years later Google is teaching the same idea again, this time with LLMs as the nodes. The graph was always the unit that scaled.

Argona's profile picture
Argona2 days ago

that timestamp breakdown is really useful

Lee_1909's profile picture
Lee_19092 days ago

Valuable resource for graph engineering enthusiasts.

rewind's profile picture
rewind2 days ago

one hour from zero to always running, wild

Nexqor's profile picture
Nexqor2 days ago

is graph engineering just a new name for what langgraph already does

Jurly's profile picture
Jurly2 days ago

self-improving graphs are where the practical value gets tested

Jordan Lee's profile picture
Jordan Lee1 day ago

bro a full hour of google teaching graph engineering? yeah i'm watching this

Related Videos