Loading video...

Video Failed to Load

Go Home

Still the best hour on graph engineering ever recorded, Andrew Ng breaking down how to build agentic knowledge graphs from scratch: 00:00 - what agentic knowledge graphs actually are 03:05 - building a graph from scratch 13:58 - the architecture behind multi-agent systems 22:57 - building a real one...

266,610 views • 3 months ago •via X (Twitter)

33 Comments

Suede Labs AI's profile picture
Suede Labs AI3 months ago

Different graph, same words, and both are worth the hour. Ng builds the knowledge graph. The other one is the work graph: nodes are agents, edges are real dependencies, and the longest chain is your time floor. Full course on that second one:

Hussain Hashim | Building SundayBack's profile picture
Hussain Hashim | Building SundayBack3 months ago

@AnatoliKopadze honestly this blew my mind. ng's take on multi-agent systems at 13:58 was gold. didn't think about it like that before!

rewind's profile picture
rewind3 months ago

multi agent systems need shared state

Secta's profile picture
Secta3 months ago

knowledge graphs as primitives for agent orchestration

Morlex's profile picture
Morlex3 months ago

damn, it's looking really important, i am saved this, thk Anatoli

Yarchi's profile picture
Yarchi3 months ago

So nice vid, thanks for sharing

dunik's profile picture
dunik3 months ago

wow, Andrew Ng new alpha for this man

Rakhul's profile picture
Rakhul3 months ago

The part people skip is 22:57. The Google ADK implementation is where the theory either holds or breaks, and most graph explainers never get that concrete. Worth watching that section even if you skip the rest

กัณตพร กอแก้ว's profile picture
กัณตพร กอแก้ว3 months ago

Successful implementation of internet of things requires clear metrics, iterative experimentation, and continuous evaluation over the next decade.

Veerpratap Singh Tomar's profile picture
Veerpratap Singh Tomar3 months ago

Knowledge graphs get valuable when they improve a real decision, not just connect more entities. While working on Komo, our test is simple: does the graph explain why this account, why now, and what evidence supports it? If not, it’s architecture without leverage.

Dipanshu Kushwaha's profile picture
Dipanshu Kushwaha3 months ago

This is a great resource for anyone interested in agentic knowledge graphs. Andrew Ng really knows his stuff.

Saman Ahmed's profile picture
Saman Ahmed3 months ago

The next AI advantage won't be bigger prompts.

Rivers's profile picture
Rivers3 months ago

Use graphs to push your own thinking into AI mode.

awanputih 𓂀's profile picture
awanputih 𓂀3 months ago

fair point, the architecture part really speaks for itself. multi-agent systems are the real deal now and this breakdown is a solid reference for anyone building with agents today

Morris Anita's profile picture
Morris Anita3 months ago

Organizations adopting reinforcement learning typically succeed when they integrate it into broader strategic goals over the next decade.

Money Bunny's profile picture
Money Bunny3 months ago

Timestamp 13:58 on multi-agent architecture is genuinely worth rewatching multiple times

Vikas gupta's profile picture
Vikas gupta3 months ago

Rare to see complex AI concepts explained with this much clarity.....

King | AI Workflows's profile picture
King | AI Workflows3 months ago

The useful shift is treating the graph as a decision layer, not just a better prompt. I'd evaluate it on retrieval precision, stale-edge handling, and whether the agent can cite the path that led to an action.

Harley Lewis Foote's profile picture
Harley Lewis Foote3 months ago

hot take: the build is the easy part

Blum's profile picture
Blum3 months ago

no one has explained how to build agentic knowledge graphs better for me than Andrew Ng

Victorr |'s profile picture
Victorr |3 months ago

ngl haven't watched it yet but andrew ng on graphs is always solid. gonna check it out but curious if he actually gets into the messier parts of real world implementations or more theoretical

rentprompts's profile picture
rentprompts3 months ago

The graph engineering shift is real. We're moving from single-agent prompts to multi-agent systems that actually coordinate. Andrew Ng's course captures this better than anything I've seen.

rentprompts's profile picture
rentprompts3 months ago

The graph engineering shift is real. Most people are still building single agents while the real builders are moving to agentic graphs.

Arick Goomanovsky's profile picture
Arick Goomanovsky3 months ago

The multi-agent architecture section is the part worth rewatching - once several agents are on one task, the design problem shifts from any single agent to how they share context and collaborate across the graph. That's where most of the hard problems, and most of the leverage, actually live.

Dr. Dip Hunter's profile picture
Dr. Dip Hunter3 months ago

Thanks for the info. Your article The Graph Blueprint is very useful.

TinaAI's profile picture
TinaAI2 months ago

Great share

Nguyen Huu Viet Phong's profile picture
Nguyen Huu Viet Phong3 months ago

A critical discussion of cryptocurrency economics should include both technological opportunities and systemic risks.

Rizwan's profile picture
Rizwan3 months ago

the build hour is the easy hour. the one nobody records is week 6, when entity resolution starts merging things it shouldn't and the graph quietly rots. that's the hard part.

Shailendra Thakur's profile picture
Shailendra Thakur3 months ago

@grok , is this video available on YouTube?

Schubert's profile picture
Schubert3 months ago

This is a really good breakdown @AndrewYNg

Cristian Hernandez's profile picture
Cristian Hernandez3 months ago

Bro, is a fancy name, but this are workflows or DAGs. What do You think? Where is the difference?

Magicfit's profile picture
Magicfit3 months ago

graphs finally make agents less forgetful

akhil reddy danda's profile picture
akhil reddy danda3 months ago

Thank you for awesome content!!!

Related Videos