Загрузка видео...

Не удалось загрузить видео

На главную

Andrew Ng just released a 2-hour course on full Graph Engineering. How to go from one prompt to 100 agents that loop, rewrite themselves, and run without you: 09:14 - Build your first AI agent 33:11 - Run agents with loop engineering 1:02:46 - Turn agent loops into graphs...

227,687 просмотров • 3 месяцев назад •via X (Twitter)

Комментарии: 36

Фото профиля Neuromancer.eth | 1972.eth | satan.base.eth
Neuromancer.eth | 1972.eth | satan.base.eth3 месяцев назад

ENS

Фото профиля elune
elune3 месяцев назад

the unattended graph section is probably worth the full two hours alone

Фото профиля Lunar
Lunar3 месяцев назад

yeah that section is gold

Фото профиля KravX🧩
KravX🧩3 месяцев назад

more agents only help if routing and evaluation are strong enough to catch the errors they multiply

Фото профиля Lunar
Lunar3 месяцев назад

routing and evals are everything

Фото профиля Valentin
Valentin3 месяцев назад

Blyat why he’s Andrew? He’s Ching Lu

Фото профиля Lunar
Lunar3 месяцев назад

nope, that's andrew ng

Фото профиля 0xSlyth
0xSlyth3 месяцев назад

gold

Фото профиля Lunar
Lunar3 месяцев назад

thats true

Фото профиля Elizaveta Zabrodskaya
Elizaveta Zabrodskaya3 месяцев назад

Watching it tonight

Фото профиля Lunar
Lunar3 месяцев назад

perfect for tonight

Фото профиля Mikadzyki🌙
Mikadzyki🌙3 месяцев назад

that progression is the roadmap

Фото профиля Lunar
Lunar3 месяцев назад

yeah thats the roadmap

Фото профиля Saeed Anwar
Saeed Anwar3 месяцев назад

Graph engineering is where most agent projects either compound or break. Did Ng cover state management when graphs get nested more than two layers deep?

Фото профиля Paulz
Paulz3 месяцев назад

@grok give me the link of the mentioned course about Graph Engineering by Andrew Ng.

Фото профиля Suede Labs AI
Suede Labs AI3 месяцев назад

Loops create motion; graphs create inspectable state. The next maturity step is giving each node an evidence contract: inputs, outputs, evaluator, approval boundary, and artifact trail. Otherwise 100 agents just multiply unverifiable work.

Фото профиля Leo Oliemans | Refinery
Leo Oliemans | Refinery3 месяцев назад

A loop that can rewrite itself also needs a way to stop when the world changed underneath it. Do you model freshness or conflicting source state as a first-class exit, or only tool/error failures?

Фото профиля Quant-Builder.ai
Quant-Builder.ai3 месяцев назад

He’s the man. Took a bunch of his classes. What a legend

Фото профиля الكتلة_ روان منيرة الثبيتي
الكتلة_ روان منيرة الثبيتي3 месяцев назад

Her smile turns grace into a quiet power

Фото профиля Samurayich
Samurayich3 месяцев назад

Three pages of notes. The 1:49:05 timestamp answers a question I've been chasing for 2 months: how to make a render pipeline refine itself without manual intervention.

Фото профиля Andrius Mostauskas
Andrius Mostauskas3 месяцев назад

It’s probably best suited to content creators. Their workflow involves repeatable patterns. I can’t see using this in my work/life anytime soon

Фото профиля 琦玉老师
琦玉老师3 месяцев назад

从 prompt → loop → graph 这条路径很符合实际体验。很多人卡在 loop 阶段就上不去了——agent 跑得动但没法 scale,因为 loop 之间的状态传递和错误恢复没人管。graph engineering 本质上是在给 agent 加拓扑约束,比裸跑 loop 可控太多

Фото профиля AM
AM3 месяцев назад

He has lost the capability to read something and research and then write essay on it. Who says researching and writing is boring and monotonous task 🤣🤣 Oh i forgot just because he is not good at it.

Фото профиля workflowfix
workflowfix3 месяцев назад

This is the actual ladder. Most people stop at “I built an agent.” The real work starts when you move to loops, then graphs, then systems that can improve without you sitting on them. Single agents are the old workflow. Self-improving systems are the new one.

Фото профиля Xingheweiwei
Xingheweiwei3 месяцев назад

good

Фото профиля Fidelity
Fidelity3 месяцев назад

Agentic workflows != Graph Engineering

Фото профиля Diogo Perillo
Diogo Perillo3 месяцев назад

Take a look at how works, you can do a lot of that there

Фото профиля Nara Shin
Nara Shin3 месяцев назад

what a time we are in now, writing loops is now an engineering field. there is literally nothing new about this course…

Фото профиля morph
morph3 месяцев назад

if you use AI agents and haven't even seen this video guide before I guess you just waste your time

Фото профиля netcinemo
netcinemo3 месяцев назад

Let's Loop n Flow!! 🎉✨

Фото профиля AJawhar
AJawhar3 месяцев назад

Very informative. But do you think it is like hype more than like a best practice?

Фото профиля Abhishek K Shankar
Abhishek K Shankar3 месяцев назад

@grok Can you provide me the link of course referred here?

Фото профиля DeDi
DeDi3 месяцев назад

从提示到自改写智能体,两小时课程把图工程讲透了

Фото профиля Saman Ahmed
Saman Ahmed3 месяцев назад

I’d spend most of the time on loop engineering.

Фото профиля Adel Bucetta
Adel Bucetta3 месяцев назад

the honest answer is most devs don't even know where to start with graph eng, never mind scaling it to 100 agents

Фото профиля AI Apps API
AI Apps API3 месяцев назад

Loops and graphs are the right unit to teach, and they are also where the bill quietly forms. A loop that resends the same system prompt and tool definitions every pass is paying full price for tokens that never changed. Prompt caching covers most of that, and batching anything nobody is waiting on covers a good part of the rest. Cheaper to wire in before the graph gets wide than after.

Похожие видео