Jonathan, the CTO, tested goals in Codex, a feature that gives coding agents persistent objectives with success criteria. He gave the agent 20-30 turns to complete a ticket but found goals aren't reliable enough for regular workflow yet.
Goals in Codex are persistent objectives in Codex that keep a thread working toward a defined outcome across turns. A goal gives Codex a completion condition. What should be true, how success should be checked, and what constraints must stay intact. Jonathan, from your CTO perspective, you were mentioning you've been using goals in Codex, or you, you had tried it. What are your thoughts?
I just tested it out. I still don't consider it like a valuable tool that I use regularly in my workflow. It's more like, you know, okay, I'll pick up a ticket from Linear, and if it has really clear acceptance criteria that I can feed into the goal, I can say like, here are allocate 20 or 30 turns towards like trying to accomplish this whole thing by yourself and see how far it can get.
I'm really not expecting it's the best way to get my work done.
I'm just kind of seeing like what's the model capable of at this moment in time. The idea here is good. I posted an article in our team learning section about, it's called What the Fuck is a Loop? Peter Steinberger versus Boris Cherny. And one of the key ideas there is like these looping agents are cool, but the underlying primitive that needs to get better is the skill. Like, if for each loop, how does this skill get good enough to achieve the thing that it's supposed to do during the loop?
