You Can Learn Loop VS Graph Engineering In 21 Min | AI Agent System Design, Harness, Nodes, Edges

35 Просмотры

Спасибо! Поделитесь с друзьями!

Вам не понравилось видео. Спасибо за то что поделились своим мнением!

Издатель Aug 2, 2026

Join community: https://seanchen.io | On July 18th, Peter Steinberger asked one question on X: are we still talking about loops, or did we shift to graphs yet? Two weeks later the whole AI agent space is arguing about whether loop engineering is dead. It isn't. A loop and a graph do two different jobs, and the systems worth building use both.

In this video I draw the entire AI agent engineering ladder on the whiteboard, from prompt to context to skills to loop to graph, so you can see where each rung came from and which one your problem actually needs. Then we open real code: Waku Agent, my open source local-first assistant, now has a graph engine, and I run two live graphs against my GitHub, my calendar, and the web. Whiteboard first, terminal second, step by step, no jargon, technical or not.

Waku Agent repo: https://github.com/ShenSeanChen/waku-agent
pip install waku-agent

Join the community at https://seanchen.io for twice-monthly live build and Q&A sessions, a private Discord, and the original .excalidraw files for every whiteboard in this series so you can open them and remix them yourself.

Check out my AI Agent Startup https://AutoManus.io, a memory system for complex B2B sales. It reads every WhatsApp, email and web chat thread, keeps a living profile of each client, and drafts the follow-up using six months of context. Free tier live, paid from $29/month;

You Can Build Anything. You Can Learn Anything.