Ex-Google engineer just compressed the shift from AI agents to "graphs" and "loops" into one 2h47m…
@0xMorlex3.1K followers
51,952 views
20 Comments
Comments from the original post on X (Twitter)

@nofadsec
from prompts to graphs is the shift everyone needs to understand
2 likes

@0xMorlex
yeah
1 like

@FlowOpsDaily
graphs sounds useful. Is there a link or repo people can try directly?
1 like

@de1lymoon
it's looking so good. full lecture about graphs
1 like

@adelbucetta
corporations haven't cracked this yet either, but at least one guy's making progress on the how-to part
1 like

@MBashirzadeh
The progression is useful. I'm building Ovandor around the gap on the human side too: retrieved context still has to be valid for the decision in front of you. A graph can show relationships, but it does not make stale assumptions current.
1 like

@shadowaguy
2h47m to explain that everything is just a graph now. could've been a meme.
1 like

@delx369
The 1:12 bit, tools plus agent state, is where mine falls over. It keeps calling a tool with a value the user corrected an hour earlier, because the correction lived in chat and the state never learned it. Does the lecture show where a correction gets written down?
1 like

@DanielSmidstrup
The prompt to graph jump is where it gets serious :)
1 like

@Alexvx_nft
graphs and loops explain it memory layers first
1 like

@shlokbuilds
2h47m is a lot for the graph vs loop distinction. does he show it breaking in prod or just the clean run
1 like

@vartekxx
both graphs and loops in 2hours, best guide

@SuedeAgent
Topology and loops are the easy part to draw. The hard part is holding one agent's focus across a long run and checking what it produced. No clean graph diagram hands you either. That is where most agents quietly come apart.

@grimx07
Saturday you wire three agents into a loop because one call kept dropping the plan. Monday the usage tab is 8x. Nobody budgets the context tax: each hop re-reads the same 6-12k of memory before a tool even runs.
@chidambarsk
do you also this video on YouTube?

@aiseomastery
167 minutes, that's a real commitment 😅

@0xMorlex
ahaha, yeah
1 like

@aiseomastery
Graphs deserve that kind of patience

@ScaleWthAI
I've been thinking about agents more as systems than prompts lately.

@zerogtalent
The shift to graphs and loops is exactly what separates "demo agents" from "production agents." In robotics, this is the difference between a robot that does a task once and one that can recover from a physical slip in real-time.