正在加载视频...

视频加载失败

Google just released a free 2-hour course on Graph & Loop engineering: 1 prompt → 100 agents → loops → graphs, from 0% to 100%: 0% → 0:35 - graph engineering from scratch 30% → 31:17 - build your first agent graph 45% → 43:40 - run hundreds of...

27,608 次观看 • 1 个月前 •via X (Twitter)

12 条评论

slash1s 的头像
slash1s1 个月前

wow I love this topic

Hussain Hashim | Building SundayBack 的头像
Hussain Hashim | Building SundayBack1 个月前

@hanakoxbt honestly never thought I'd need to deep dive into graph engineering, but now I see how running parallel agents can elevate workflows. Might give this course a shot!

RemoteBrowser 的头像
RemoteBrowser1 个月前

Running hundreds of agents in parallel is where the graph gets interesting. The hard part isn't spawning them, it's the fan-in: partial failures, retries, and keeping state consistent when one branch stalls. How are you handling that merge step?

Leliu 的头像
Leliu1 个月前

Interesting concept for scaling AI agent capabilities.

SEO Mastery 的头像
SEO Mastery1 个月前

100 agents running in parallel, wild scale

Aryan Pegwar 的头像
Aryan Pegwar1 个月前

I have watched the complete video course and created a skill for implementing the learnings immediately in all my agentic AI workflows. If someone wants that I'll happily share. Just DM me. "Skill"

Miles S. 的头像
Miles S.1 个月前

100 agents in parallel is the bit i’d watch first

John Mercier 的头像
John Mercier1 个月前

One agent works. A loop makes it compound.

Crio Songo 的头像
Crio Songo1 个月前

刚好最近在做多智能体架构,这个点说到点子上了,我这就去找课程来学学怎么搭分层结构。

SpectraView 的头像
SpectraView1 个月前

Just two hours of your time, and you become better.

Thành Lê 🌩️ 的头像
Thành Lê 🌩️1 个月前

Beautif course

Kuzka_aaa 的头像
Kuzka_aaa1 个月前

The real jump isn’t a better prompt. It’s going from 1 agent stuffed with instructions to a graph that fans out, checks itself, and keeps running while you sleep.Same model. Different shape.

相关视频