Cursor's Third Era: Cloud Agents

**Samantha** (0:00)
So this is another experiment that we ran last year and didn't decide to ship at that time, but may come back to. LM Judge, but one that was also agentic and could write code. So it wasn't just picking, but also taking the learnings from two models or N models that it was looking at and writing a new diff. And what we found was that there were strengths to using models from different model providers as the base level of this process. Basically, you could get almost like a synergistic output that was better than having a very unified, like bottom model tier.

**Jonas** (0:30)
We think that over the coming months, the big unlock is not going to be one person with a model getting more done, like the water flowing faster, and we'll be making the pipe much wider. So paralyzing more, whether that's swarms of agents or parallel agents, both of those are things that contribute to getting much more done in the same amount of time.

**swyx** (0:53)
This week, one of the biggest launches that Cursor has ever done is Cloud Agents. I think you had Cloud Agents before, but this was like you give Cursor a computer, right? So is this basically they bought Autotab, and then they repackaged it, is that what's going on?

**Jonas** (1:09)
That's a big part of it, yeah. Cloud Agents already ran in their own computers, but they were sort of sight reading code. And those computers were not, they were like blank VMs typically that were not set up for the DevEx for whatever repo the agent's working on. One of the things that we talk about is, if you put yourself in the model shoes, and you were seeing tokens stream by, and all you could do was sight read code and spit out tokens and hope that you had done the right thing.

**swyx** (1:33)
No chance.

**Jonas** (1:34)
I'd be so bad. Obviously, you need to run the code. And so that, I think, also is probably not that contrarian of a take, but no one has done that yet. And so giving the model the tools to onboard itself and then use full computer use, end-to-end, pixels in, coordinates out, and have the cloud computer with different apps in it is the big unlock that we've seen internally in terms of usage of this, going from, oh, we use it for little copy changes, to know we're really driving new features with this kind of new type of agentic workflow.

**swyx** (2:07)
All right, let's see it.

**Jonas** (2:08)
Cool. So this is what it looks like in cursor.com/agents. So this is one I kicked off a while ago. So on the left-hand side is the Chad, very classic sort of agentic thing. The big new thing here is that the agent will test its changes. So you can see here, it worked for half an hour. That is because it not only took time to write the tokens of code, it also took time to test them end-to-end. So it started dev servers iterate when needed. And so that's one part of it is like model works for longer and doesn't come back with a, I tried some things PR, but I tested that PR that's ready for your review. One of the other intuition pumps we use there is if a human gave you PR, asked you to review it and they hadn't tested it, you'd also be annoyed because you'd be like, only ask me for a review once it's actually ready. So that's what we've done with.

**swyx** (2:56)
Simple question I wanted to gather our friends. Some PRs are way smaller, like just copy change. Does it always do the video or is it sometimes?

**Jonas** (3:03)
Sometimes.

**swyx** (3:04)
So what's the judgment?

**Jonas** (3:05)
The model does it. So we do some default prompting with sort of what types of changes to test. There's a slash command that people can do called slash no test, where if you do that, the model will not test. But the default is test. The default is to be calibrated. So we tell it, don't test very simple copy changes, but test more complex things. And then users can also write their agents.md and specify this type of, if you're editing this subpart of my mono repo, never tested because that won't work or whatever. So pillar one is the model actually testing. Pillar two is the model coming back with a video of what it did. We have found that in this new world where agents can end-to-end write much more code, reviewing the code is one of these new bottlenecks that crop up. And so reviewing a video is not a substitute for reviewing code, but it is an entry point that is much, much easier to start with than glancing at some giant diff. And so typically you kick one off, it's done, you come back, and the first thing that you would do is watch this video. So this is a video of it. In this case, I wanted a tool tip over this button, and so it went and showed me what that looks like in this video.