正在加载视频...

视频加载失败

Google just released a 1-hour course on “Context Engineering” for AI agents from scratch: • 00:00 - Introduction to “Context Engineering” • 03:02 - Context Engineering vs “prompting” • 16:18 - Build a context brain for your agent • 22:10 - Building agent context (tools, skills) • 29:06 -...

14,822 次观看 • 1 个月前 •via X (Twitter)

25 条评论

Jake Van Clief 的头像
Jake Van Clief1 个月前

Just use ICM

Granite 的头像
Granite1 个月前

every context course teaches you to add more unfortunately i've bought courses like that, and i'm sure this video covers most of the paid material

Movez 的头像
Movez1 个月前

Google explains how to build context differently, bro.

Mayor. 的头像
Mayor.1 个月前

good share

Movez 的头像
Movez1 个月前

Thx Mayor !

Genius💡💹🧲 🤖 的头像
Genius💡💹🧲 🤖1 个月前

The future belongs to agents with context, not just clever prompts

Movez 的头像
Movez1 个月前

the future is agents building agents, that are building their context

Gipp 🦅 的头像
Gipp 🦅1 个月前

the tools and skills section shows context is more than prompts

Movez 的头像
Movez1 个月前

Yeah. This is true Gip. And it’s very important to work with Context correctly for long running AI systems

rewind 的头像
rewind1 个月前

one hour could change workflows

Leo Amos 的头像
Leo Amos1 个月前

Context engineering being a whole course now is wild, it was the invisible job a year ago. Even (building it) handles context structurally so agents arrive with the right state, not a wall of text.

Anoy 的头像
Anoy1 个月前

So 'Context Engineering' is just what we’re calling 'Prompting' now that it has a LinkedIn profile?

karcharodon 的头像
karcharodon1 个月前

Learning something is now very easy people just need to focus on t

dunik 的头像
dunik1 个月前

Context Engineering change this AI-meta thank you

Vermis 的头像
Vermis1 个月前

love this

Gill 的头像
Gill1 个月前

Context engineering is definitely the next major high paying tech skill.

Yarchi 的头像
Yarchi1 个月前

the memory bank section at is the one

Victoria 的头像
Victoria1 个月前

One hour on context engineering means the gap wasn't tooling, it was people feeding the model wrong

Modelplane 的头像
Modelplane1 个月前

Agents are great at refactors, but verification is the bottleneck. Instrumenting the whole pipeline — model, prompt, code diff — is the only way to audit results later. Tools like give you that trail.

Hustle in IT 的头像
Hustle in IT1 个月前

free google drop on context engineering hits different, the memory bank part is what most paid courses skip

sindikitil 的头像
sindikitil1 个月前

Solid resource. Context management is still the biggest bottleneck for most agent implementations I've seen in production.

Mister 的头像
Mister1 个月前

This video has closed caption. Why can't Grok summarize this. There are hundreds of hour long talks. I don't have time for them. @elonmusk @grok @SpaceXAI @X

Rouzbeh 的头像
Rouzbeh1 个月前

Context engineering is still under-discussed compared to prompt engineering. Most agent failures I see come from messy or incomplete context, not from the model itself.

1mpulse 的头像
1mpulse1 个月前

It is great 1-hour course to watch, well done Movez

Mister 的头像
Mister1 个月前

Excuse me Sir where is the original video? This is stitched together.

相关视频