Загрузка видео...

Не удалось загрузить видео

На главную

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 просмотров • 3 месяцев назад •via X (Twitter)

Комментарии: 33

Фото профиля Suede Labs AI
Suede Labs AI3 месяцев назад

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:

Фото профиля Hussain Hashim | Building SundayBack
Hussain Hashim | Building SundayBack3 месяцев назад

@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!

Фото профиля rewind
rewind3 месяцев назад

multi agent systems need shared state

Фото профиля Secta
Secta3 месяцев назад

knowledge graphs as primitives for agent orchestration

Фото профиля Morlex
Morlex3 месяцев назад

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

Фото профиля Yarchi
Yarchi3 месяцев назад

So nice vid, thanks for sharing

Фото профиля dunik
dunik3 месяцев назад

wow, Andrew Ng new alpha for this man

Фото профиля Rakhul
Rakhul3 месяцев назад

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

Фото профиля กัณตพร กอแก้ว
กัณตพร กอแก้ว3 месяцев назад

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

Фото профиля Veerpratap Singh Tomar
Veerpratap Singh Tomar3 месяцев назад

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.

Фото профиля Dipanshu Kushwaha
Dipanshu Kushwaha3 месяцев назад

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

Фото профиля Saman Ahmed
Saman Ahmed3 месяцев назад

The next AI advantage won't be bigger prompts.

Фото профиля Rivers
Rivers3 месяцев назад

Use graphs to push your own thinking into AI mode.

Фото профиля awanputih 𓂀
awanputih 𓂀3 месяцев назад

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

Фото профиля Morris Anita
Morris Anita3 месяцев назад

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

Фото профиля Money Bunny
Money Bunny3 месяцев назад

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

Фото профиля Vikas gupta
Vikas gupta3 месяцев назад

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

Фото профиля King | AI Workflows
King | AI Workflows3 месяцев назад

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.

Фото профиля Harley Lewis Foote
Harley Lewis Foote3 месяцев назад

hot take: the build is the easy part

Фото профиля Blum
Blum3 месяцев назад

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

Фото профиля Victorr |
Victorr |3 месяцев назад

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

Фото профиля rentprompts
rentprompts3 месяцев назад

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.

Фото профиля rentprompts
rentprompts3 месяцев назад

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

Фото профиля Arick Goomanovsky
Arick Goomanovsky3 месяцев назад

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.

Фото профиля Dr. Dip Hunter
Dr. Dip Hunter3 месяцев назад

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

Фото профиля TinaAI
TinaAI2 месяцев назад

Great share

Фото профиля Nguyen Huu Viet Phong
Nguyen Huu Viet Phong3 месяцев назад

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

Фото профиля Rizwan
Rizwan3 месяцев назад

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.

Фото профиля Shailendra Thakur
Shailendra Thakur3 месяцев назад

@grok , is this video available on YouTube?

Фото профиля Schubert
Schubert3 месяцев назад

This is a really good breakdown @AndrewYNg

Фото профиля Cristian Hernandez
Cristian Hernandez3 месяцев назад

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

Фото профиля Magicfit
Magicfit3 месяцев назад

graphs finally make agents less forgetful

Фото профиля akhil reddy danda
akhil reddy danda3 месяцев назад

Thank you for awesome content!!!

Похожие видео