正在加载视频...

视频加载失败

IBM just released a 1-hour course on building agentic knowledge graphs from scratch: • 00:00 - Introduction to knowledge graphs • 05:35 - Building your first agentic graph • 19:59 - Agentic memory powered by graphs • 30:39 - Graphs for multi-agent orchestration This 1-hour watch will replace 10...

278,420 次观看 • 3 个月前 •via X (Twitter)

39 条评论

纳米AI 的头像
纳米AI3 个月前

这种讲解风格 好像王自如也做过,还讲解过怎么制作 应该是人单独录一版 书写一版,再剪辑制作 不然从正面看 人的书写,观众视角来看,字应该是反过来的

Gipp 🦅 的头像
Gipp 🦅3 个月前

that 30:39 multi-agent orchestration section sounds like the standout here

Codez 的头像
Codez3 个月前

Basiclly Graphs are made for Multi-agents orchestration, and this part is a pure gold

Granite 的头像
Granite3 个月前

his writing is really easy to read i like this approach, thanks for sharing

Codez 的头像
Codez3 个月前

Yeah, basically knowledge graphs explained simply.

rewind 的头像
rewind3 个月前

one hour covers the whole graph stack

Codez 的头像
Codez3 个月前

Yeah, true - if you watch this, you’re basically at master degree level in graph engineering. Just apply it to your agent stack and you’re gucci.

M 的头像
M3 个月前

Thanks for sharing, though pretty sure this was from 4 years ago?

꧁EVGENIA꧂ 的头像
꧁EVGENIA꧂3 个月前

thanks for the courses, I added them to my bookmarks

Codez 的头像
Codez3 个月前

You are welcome Evgenia. Whats your favorite btw ?

vartekx 的头像
vartekx3 个月前

wow man, that’s a pure gold material on graph engineering!

Codez 的头像
Codez3 个月前

Yeah, IBM has been shipping real alpha for years, and this watch is one of them.

Fokki 的头像
Fokki3 个月前

This is what I needed

Codez 的头像
Codez3 个月前

All you need to master Graphs is to spend 1 hour on this video!

Johnny Suede 的头像
Johnny Suede3 个月前

Graphs earn their keep at reconciliation, not recall. Storing what happened is easy. Deciding which of two conflicting facts survives is the part that needs structure, and where most memory layers quietly do nothing.

Brandon Kase 的头像
Brandon Kase3 个月前

In order to deeply understand multi-agent orchestration graphs, it’s so important to build a strong foundation with the core agent loops and “loops” like /goal and /autoresearch . @christinetyip and I review these fundamentals before discussing subagent graphs in our latest episode.

Hussain Hashim | Building SundayBack 的头像
Hussain Hashim | Building SundayBack3 个月前

@0xCodez 1 hour isn't bad for all that. Do they go deep into agentic memory? That's what I'm most curious about.

Carry 的头像
Carry3 个月前

ibm really said let us cook one more time 1 hour to replace 10 courses is either genius or the other 10 were just padding lol

eXsoR 的头像
eXsoR3 个月前

@Whimsicali you seen this?

Syed Sadiq Ali 的头像
Syed Sadiq Ali3 个月前

Just release? can you provide the link?

Enashka 的头像
Enashka3 个月前

Dude, I went to watch it on youtube to realize that video is 4 years old.

AI超能力日记 by AI Skill Market 的头像
AI超能力日记 by AI Skill Market3 个月前

@IBMwatsonx 这种已经不在牌桌上的教别人用Agentic graphs,有时间把自己的Bob产品打磨好。

Diego Sanmartin 的头像
Diego Sanmartin3 个月前

Damm, I guess I was too early in 2023 talking about it…

Tiger 的头像
Tiger3 个月前

Multi-agent systems eventually become a state-management problem. Chunks can store information, but graphs can represent who knows what, what changed, and why a decision was made.

Blockey 的头像
Blockey3 个月前

Thanks for sharing.

AI Mastery Guide 的头像
AI Mastery Guide3 个月前

An hour to replace 10 courses, bookmarking this one for the weekend 📚

Pradeep Silva 的头像
Pradeep Silva3 个月前

Organizations adopting neural networks typically succeed when they integrate it into broader strategic goals in emerging economies.

Vipul Kumar Kewat 的头像
Vipul Kumar Kewat3 个月前

Knowledge graphs are becoming a powerful foundation for building smarter ai systems. Combining structured knowledge with agent workflows can unlock more reliable reasoning, memory, and multi agent collaboration.

spuliz 的头像
spuliz3 个月前

Graphs add value when they improve reasoning, not just storage. Connecting entities, relationships, and provenance gives agents a stronger foundation for retrieval and decision-making.

Shubham Sharma | AI & Tech 的头像
Shubham Sharma | AI & Tech3 个月前

knowledge graph engineer wasnt even on my radar last year now its looking like the move fr.

The Holy City Gambler 的头像
The Holy City Gambler3 个月前

Yea...lets listen to the Watson guys about how to build shit. Dont get me wrong appreciate the thought behind it but you have actual industry leaders dropping thought pieces and instructional content every other day lmfao

𝛼 ✨ 的头像
𝛼 ✨3 个月前

I confirm this is real α

MostAgile | TechLead187 的头像
MostAgile | TechLead1873 个月前

Yeah I did this already, but I’ll see if there are any nuggets I missed.

l1ndle 的头像
l1ndle3 个月前

one hour can teach the pattern - production graphs still need schema migrations, provenance and failure recovery

Сarm1ne 的头像
Сarm1ne3 个月前

this replaces a stack of paid courses, save it now

Nick Venturi 的头像
Nick Venturi3 个月前

bookmarking this to pretend i will watch it this weekend

starmex 的头像
starmex3 个月前

martin keen at a whiteboard is the most trusted format in this whole niche

Aqib Khan 的头像
Aqib Khan3 个月前

This is how a typical agent orchestrator looks like managing your tools, memory and agents.

Johnny Suede 的头像
Johnny Suede3 个月前

Knowledge graphs are having a moment because everyone hit the same wall with RAG. Chunks give you recall, graphs give you provenance. The moment you need to say where a claim came from, the graph is the only one that answers.

相关视频