Skip navigation
Ex-Google engineer just compressed the shift from AI agents to "graphs" and "loops" into one 2h47m…
0:00 / 2:47:42

Ex-Google engineer just compressed the shift from AI agents to "graphs" and "loops" into one 2h47m…

Morlex

@0xMorlex3.1K followers

Visit on X
525 likesDownloadOriginal post

51,952 views

Ex-Google engineer just compressed the shift from AI agents to "graphs" and "loops" into one 2h47m lecture: • 00:00 - understanding the different layers of AI memory • 30:00 - moving from simple LLM calls to AI agents • 50:00 - why agent systems are becoming a graph engineering problem • 1:12:00 - connecting context, tools and agent state • 1:24:00 - building a minimal agent harness from scratch • 1:46:00 - breaking down the architecture behind Hermes Agent • 2:08:00 - turning agent concepts into working systems 167-minute deep dive, and one of the clearest ways to understand how AI engineering is moving beyond prompts The progression: Prompt → Context → Memory → Agent → Loop → Graph → Agent Harness Watch it today, then read the full roadmap below

20 Comments

Comments from the original post on X (Twitter)

  • nofad's profile picture

    @nofadsec

    from prompts to graphs is the shift everyone needs to understand

    2 likes

  • Morlex's profile picture

    @0xMorlex

    yeah

    1 like

  • FlowOps Daily's profile picture

    @FlowOpsDaily

    graphs sounds useful. Is there a link or repo people can try directly?

    1 like

  • Alex's profile picture

    @de1lymoon

    it's looking so good. full lecture about graphs

    1 like

  • Adel Bucetta's profile picture

    @adelbucetta

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

    1 like

  • mohsen bashirzadeh's profile picture

    @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's profile picture

    @shadowaguy

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

    1 like

  • David Batista's profile picture

    @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

  • Daniel Smidstrup's profile picture

    @DanielSmidstrup

    The prompt to graph jump is where it gets serious :)

    1 like

  • ALEXYZ's profile picture

    @Alexvx_nft

    graphs and loops explain it memory layers first

    1 like

  • Shlok Madhekar's profile picture

    @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

  • vartekx's profile picture

    @vartekxx

    both graphs and loops in 2hours, best guide

  • Suede Labs AI's profile picture

    @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.

  • grim · vibe coding final boss's profile picture

    @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.

  • Chidambar Kulkarni's profile picture

    @chidambarsk

    do you also this video on YouTube?

  • AI Mastery Guide's profile picture

    @aiseomastery

    167 minutes, that's a real commitment 😅

  • Morlex's profile picture

    @0xMorlex

    ahaha, yeah

    1 like

  • AI Mastery Guide's profile picture

    @aiseomastery

    Graphs deserve that kind of patience

  • Saman Ahmed's profile picture

    @ScaleWthAI

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

  • Zero G Talent's profile picture

    @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.