Google just released free 2-hour course on full agent engineering: 1 prompt → agent teams → loops → graphs from 0% to 100%: 10% → 38:46 - build your first agent 30% → 54:46 - connect MCP tools 55% → 1:12:43 - Loop engineering: 4 ways to run agents... 70% → 1:20:57 - Graph engineering 100% → 2:22:31 - the full system that works while you sleep most people build one agent and stop there - this is the full path to a system that runs without you from scratch watch it today - then read the full graph engineering playbook below ↓show more

what a brilliant material broski 2 hours workshop from 0, saved!

ye, and this is suitable for both beginners and professionals thank you for supp

the system that works while you sleep also fails while you sleep. ask me how i know

saved. the graph engineering section alone is worth it

huh, for now it's most hype and most useful tecnology so everyone should know how to use it

Do you have a YouTube link?

Two hours from one prompt to full agent graphs is a pretty solid free course

it is, absloutely worth to watch!

I love Annie Wang ♥️ ❤️

The graph section is the one to slow down on. Most teams get agent teams running and then find the hard problem was never orchestration, it was deciding what each node is allowed to see.

great video. love having timestamps to jump around

Can anyone tell me Annie Wang's X I'd. Please

what a useful piece of material, thanks Codila

where is this from? can I get exact link

She is too cute to listen what she’s saying

codila this is exactly right. most people stop at one agent, but the orchestration and graph parts are where things get autonomous. I saw Google's recent AI agents intensive pulled 1.5M learners, so the appetite for this is real.

Why the f would I ever want 1000 agents to run?

Where it's link

No crees que el uso de muchos agentes consume mas tokens? Actualmente tengo estos agentes y creo que consumo aumento backend-engineer.md domain-logic.md qa.md orchestrator.md frontend-engineer.md security-auditor.md

A two-hour course is useful when it teaches the whole loop: define the task, give the agent tools, inspect the trace, and recover from failure. The architecture matters more than memorizing another framework name.

Thanks for sharing.

Who's gonna pay for da tokens

This is what I'm looking for. Thanks

For everyone asking -

They will depreciate it soon. don’t worry.

After this course, can you actually build a system that runs 24/7 without you, or do you still have to constantly fix it?

@0xSwaroski

Agents need a safe last mile: publish on the user's logged-in machine, not a shared cloud session. PublishPort:

The progression makes sense. Single agents are useful, but orchestration, tools, and evaluation are what turn them into reliable systems

bro , thoda ruko yrrrr , abhi to loop aaya tha . thoda toh wait kar lo

I just did the equivalent of this process in a few minutes of in Claude. What am I missing?

Do you have youtube link for this? Thx

Please paste the video link.

@grok is this video from Google ?

They’re behind in the AI race.

how do i get access to the full course