正在加载视频...

视频加载失败

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 次观看 • 3 个月前 •via X (Twitter)

33 条评论

Suede Labs AI 的头像
Suede Labs AI3 个月前

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 的头像
Hussain Hashim | Building SundayBack3 个月前

@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 的头像
rewind3 个月前

multi agent systems need shared state

Secta 的头像
Secta3 个月前

knowledge graphs as primitives for agent orchestration

Morlex 的头像
Morlex3 个月前

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

Yarchi 的头像
Yarchi3 个月前

So nice vid, thanks for sharing

dunik 的头像
dunik3 个月前

wow, Andrew Ng new alpha for this man

Rakhul 的头像
Rakhul3 个月前

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 的头像
กัณตพร กอแก้ว3 个月前

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

Veerpratap Singh Tomar 的头像
Veerpratap Singh Tomar3 个月前

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 的头像
Dipanshu Kushwaha3 个月前

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

Saman Ahmed 的头像
Saman Ahmed3 个月前

The next AI advantage won't be bigger prompts.

Rivers 的头像
Rivers3 个月前

Use graphs to push your own thinking into AI mode.

awanputih 𓂀 的头像
awanputih 𓂀3 个月前

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 的头像
Morris Anita3 个月前

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

Money Bunny 的头像
Money Bunny3 个月前

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

Vikas gupta 的头像
Vikas gupta3 个月前

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

King | AI Workflows 的头像
King | AI Workflows3 个月前

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 的头像
Harley Lewis Foote3 个月前

hot take: the build is the easy part

Blum 的头像
Blum3 个月前

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

Victorr | 的头像
Victorr |3 个月前

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 的头像
rentprompts3 个月前

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 的头像
rentprompts3 个月前

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

Arick Goomanovsky 的头像
Arick Goomanovsky3 个月前

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 的头像
Dr. Dip Hunter3 个月前

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

TinaAI 的头像
TinaAI2 个月前

Great share

Nguyen Huu Viet Phong 的头像
Nguyen Huu Viet Phong3 个月前

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

Rizwan 的头像
Rizwan3 个月前

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 的头像
Shailendra Thakur3 个月前

@grok , is this video available on YouTube?

Schubert 的头像
Schubert3 个月前

This is a really good breakdown @AndrewYNg

Cristian Hernandez 的头像
Cristian Hernandez3 个月前

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

Magicfit 的头像
Magicfit3 个月前

graphs finally make agents less forgetful

akhil reddy danda 的头像
akhil reddy danda3 个月前

Thank you for awesome content!!!

相关视频