Member-only story
Featured
Graph Engineering Explained: What Actually Changed #
If you spend any time in the AI Twitter bubble, you saw this one. Nine words from Peter Steinberger, the creator of OpenClaw, that pulled 2.6 million views as I’m recording this. Probably even more when you are watching. Then Hamel Husain, famously known for AI evals, piled on: “Loop engineering is dead. Enter graph engineering.” And just like that, my whole feed decided we have a new discipline. Watch the video version
[here]for the full experience! To be honest, both tweets were jokes. Steinberger was poking at how fast we rename things. Prompt engineering became context engineering, then harness engineering, and then loop engineering. Which all MOSTLY means the same. But jokes go viral when they’re pointing at something real and relatable, and this one is. Even for us, the regular folks that don’t have an OpenAI employee’s budget.
I made a video on loop engineering a few weeks ago, and apparently it died before some of you even got a chance to watch it. Now, let’s cover what graph engineering actually is, and which part deserves your attention, because one thing did quietly change, and there’s some interesting stuff in this vastly overhyped fuss, and it’s not the graph part.