Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

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...

227,754 Aufrufe • vor 3 Monaten •via X (Twitter)

36 Kommentare

Profilbild von Neuromancer.eth | 1972.eth | satan.base.eth
Neuromancer.eth | 1972.eth | satan.base.ethvor 3 Monaten

ENS

Profilbild von elune
elunevor 3 Monaten

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

Profilbild von Lunar
Lunarvor 3 Monaten

yeah that section is gold

Profilbild von KravX🧩
KravX🧩vor 3 Monaten

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

Profilbild von Lunar
Lunarvor 3 Monaten

routing and evals are everything

Profilbild von Valentin
Valentinvor 3 Monaten

Blyat why he’s Andrew? He’s Ching Lu

Profilbild von Lunar
Lunarvor 3 Monaten

nope, that's andrew ng

Profilbild von 0xSlyth
0xSlythvor 3 Monaten

gold

Profilbild von Lunar
Lunarvor 3 Monaten

thats true

Profilbild von Elizaveta Zabrodskaya
Elizaveta Zabrodskayavor 3 Monaten

Watching it tonight

Profilbild von Lunar
Lunarvor 3 Monaten

perfect for tonight

Profilbild von Mikadzyki🌙
Mikadzyki🌙vor 3 Monaten

that progression is the roadmap

Profilbild von Lunar
Lunarvor 3 Monaten

yeah thats the roadmap

Profilbild von Saeed Anwar
Saeed Anwarvor 3 Monaten

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?

Profilbild von Paulz
Paulzvor 3 Monaten

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

Profilbild von Suede Labs AI
Suede Labs AIvor 3 Monaten

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.

Profilbild von Leo Oliemans | Refinery
Leo Oliemans | Refineryvor 3 Monaten

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?

Profilbild von Quant-Builder.ai
Quant-Builder.aivor 3 Monaten

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

Profilbild von الكتلة_ روان منيرة الثبيتي
الكتلة_ روان منيرة الثبيتيvor 3 Monaten

Her smile turns grace into a quiet power

Profilbild von Samurayich
Samurayichvor 3 Monaten

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.

Profilbild von Andrius Mostauskas
Andrius Mostauskasvor 3 Monaten

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

Profilbild von 琦玉老师
琦玉老师vor 3 Monaten

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

Profilbild von AM
AMvor 3 Monaten

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.

Profilbild von workflowfix
workflowfixvor 3 Monaten

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.

Profilbild von Xingheweiwei
Xingheweiweivor 3 Monaten

good

Profilbild von Fidelity
Fidelityvor 3 Monaten

Agentic workflows != Graph Engineering

Profilbild von Diogo Perillo
Diogo Perillovor 3 Monaten

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

Profilbild von Nara Shin
Nara Shinvor 3 Monaten

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

Profilbild von morph
morphvor 3 Monaten

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

Profilbild von netcinemo
netcinemovor 3 Monaten

Let's Loop n Flow!! 🎉✨

Profilbild von AJawhar
AJawharvor 3 Monaten

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

Profilbild von Abhishek K Shankar
Abhishek K Shankarvor 3 Monaten

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

Profilbild von DeDi
DeDivor 3 Monaten

从提示到自改写智能体,两小时课程把图工程讲透了

Profilbild von Saman Ahmed
Saman Ahmedvor 3 Monaten

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

Profilbild von Adel Bucetta
Adel Bucettavor 3 Monaten

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

Profilbild von AI Apps API
AI Apps APIvor 3 Monaten

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.

Ähnliche Videos