{"slug": "how-antithesis-turned-exe-into-a-sandbox-for-agentic-software-tests", "title": "How Antithesis Turned exe into a Sandbox for Agentic Software Tests", "summary": "Antithesis software engineer Carl Sverre uses exe, a VM platform, as a sandbox for agentic AI software tests, citing its per-user pricing model ($25/user/month for up to 50 VMs), root access, and non-hibernating idle VMs as key advantages over competitors. Sverre integrated exe into his workflow for testing open-source projects and developing Antithesis' command-line tool Snouty, and he filed a feature request that was implemented within days by exe engineer Philip Zeyliger.", "body_md": "Carl Sverre spends a lot of time thinking about how to give AI agents the right amount of power. Give them too little, and they can’t do real work. Give them too much, and they might blow up your tech stack. As a software engineer at [Antithesis](https://antithesis.com/), an autonomous software testing platform, that question is core to how Sverre thinks about designing tools in the era of advanced AI.\n\nThe solution he found began with figuring out the ideal place for agents to work. At the start of this exploration, he tried out the obvious options but found himself frustrated by their restrictions. Local sandboxes in particular were too limiting. \"As soon as the AI wants to do something out of that boundary, it gets blocked,\" Sverre explains. The bigger platforms, in contrast, were designed for shipping AI products. What he actually wanted was something simpler: \"I just realized what I wanted was, like, a computer,\" he says.\n\nThat’s when Sverre remembered exe. “I was like, ‘oh, yeah, like, David is doing this weird little AI project,’” he says. He signed up and launched his first VM. “I was just so impressed by the UX,” he says. “It was so easy. And then the pricing model was perfect. It solves, in my opinion, the most critical issue with sandboxes.”\n\nThat issue, in a nutshell, is that many sandbox providers charge per VM. Spin up ten sandboxes, and you pay for all ten, whether or not you’re using them simultaneously.\n\nExe works differently. A team account, which costs $25 per user per month, gives each person access to up to 50 VMs that draw from their own pool of resources. Nobody has to track how many they’re running or whether they’ve remembered to shut them down. \"I don't want to ever have to feel like I'm spending money when I create a sandbox,\" Sverre says. \"I shouldn't have to worry about my finance team asking me why I spent another two dollars.\"\n\nSverre quickly incorporated exe into his workflow. As a bug catcher, a lot of his work revolves around testing open source projects. \"I basically just changed my workflow to be like, spin up an exe machine, check out the project, open up Claude, ask a bunch of questions, and then throw away the VM,\" he says.\n\nSome projects, however, need more than a one-off VM. Sverre does much of the development for [Snouty](https://github.com/antithesishq/snouty), Antithesis’ command line tool, inside a persistent machine. \"I have Claude running there and I drive that VM through Claude remote control,\" he says. \"I basically just have access to a persistent Claude session on my phone and on the web browser.\"\n\nIn exe’s early days, Sverre noticed that any user could click a button and share their VM with the public. “I immediately was like, that's just not a thing we can have,\" he says. Luckily, with a small startup, that was an easy fix.\n\nSverre filed a feature request with exe engineer Philip Zeyliger. \"Two or three days later, it showed up in the product,\" Sverre says. The solution—restricting who can make a VM public—allowed him to roll exe out more broadly. \"I don't have to worry as much,\" he says.\n\nSverre keeps coming back to two core differentiators. First, root access: \"We love the fact that you have root on the VM. So the AI can do basically whatever it needs to do to accomplish some task, which is really nice,” he says.\n\nSecond, how exe handles idle VMs. \"Every other VM platform on the planet hibernates your VMs,\" he says. \"Exe is the only one that doesn't do that.\" In practice, it works out the same—an idle VM's resources get used by other VMs instead—but there’s no delay when an idle VM boots back up. \"You never have to think about, is it running, is it not running.”\n\nSverre is now thinking about what an expanded version of this workflow could look like—VMs that spin up other VMs and divide up work automatically. \"I'm right on the edge of building more of an automated software factory where I want to have VMs be created by other VMs,\" he says. It's still early days, but the underlying question hasn't changed: how much power do you give an agent to work—and how do you make sure it’s totally safe?\n\n\"There's this tension between giving them enough power and then also not letting them destroy the world,\" Sverre says. \"exe is that solution for us.\"", "url": "https://wpnews.pro/news/how-antithesis-turned-exe-into-a-sandbox-for-agentic-software-tests", "canonical_source": "https://blog.exe.dev/how-antithesis-turned-exe-into-a-sandbox-for-agentic-software-tests", "published_at": "2026-07-21 00:00:00+00:00", "updated_at": "2026-07-22 13:07:04.509989+00:00", "lang": "en", "topics": ["ai-agents", "developer-tools", "ai-infrastructure"], "entities": ["Antithesis", "Carl Sverre", "exe", "Snouty", "Philip Zeyliger", "Claude"], "alternates": {"html": "https://wpnews.pro/news/how-antithesis-turned-exe-into-a-sandbox-for-agentic-software-tests", "markdown": "https://wpnews.pro/news/how-antithesis-turned-exe-into-a-sandbox-for-agentic-software-tests.md", "text": "https://wpnews.pro/news/how-antithesis-turned-exe-into-a-sandbox-for-agentic-software-tests.txt", "jsonld": "https://wpnews.pro/news/how-antithesis-turned-exe-into-a-sandbox-for-agentic-software-tests.jsonld"}}