Expo Launches Cloud Simulators for AI Coding Agents
As mobile’s bottleneck shifts from writing code to verifying it, Expo Simulators lets coding agents build, run, and verify mobile apps on simulators in the cloud
Expo, the agentic mobile infrastructure used by millions of developers and AI agents to build apps for iOS, Android, and the web, launched Expo Simulators, cloud iOS simulators and Android emulators built for AI coding agents. The simulators allow agents to reproduce a reported bug, write and test a fix, verify it on iOS simulators and Android emulators, and deliver evidence of the fix for a developer to review.
As AI coding agents continue to write code faster than engineering teams can test and review it, verification has become the new bottleneck in software. On mobile, that verification process is even harder to speed up. An agent that can’t run the app can’t see what the app actually does. iOS simulators run only on Apple hardware, while cloud agents typically run on Linux. Agents use local simulators and open and manage them on a developer’s behalf, but they’re limited to what their machine can do. For example, running seven agents in parallel on a laptop can require seven simulators or emulators, and Android emulators can use 4+ GB of RAM each. As a result, developers running several agents can hit bottlenecks caused by the limited capacity of their machines.
Read more – Optiv Expands Threat Exposure Management Services
With Expo Simulators, a bug report filed in a tool such as Linear goes to an agent, which autonomously reproduces, fixes, and tests it on cloud simulators, in parallel and off the developer’s machine. Each session leaves a screen recording, screenshots, and logs on the pull request, and anyone on the team can open the running build from a link, with no TestFlight build. It works with the agents teams already use, including Cursor, Claude Code, and Codex. With no Mac needed, teams can run the iOS simulator on Linux, on Windows through WSL, or in a cloud sandbox. Expo Simulators adds no AI model of its own.
Expo calls this agentic mobile infrastructure or the infrastructure that lets agents, and the people directing them, build, verify, ship, and monitor mobile apps. Expo already provides builds, CI/CD, app store submission, over-the-air updates, and monitoring. Expo Simulators adds verification, so an agent can check its own work before a person reviews it.
Read more – DuPont Partners with Microsoft and NobleAI to Advance AI
“On the web, fixing a bug can be as easy as clicking merge. On mobile, every release goes through the app store, and users might be running 10 or 20 different versions of an app at once,” said James Ide, co-founder and CTO of Expo. “The agent was the fast part. Expo Simulators gives every agent a simulator, so a fix arrives for review already tested on several simulators, and the only decision left is whether it’s the right code. Watch it run, then merge.”
Expo Simulators are available today to everyone on Expo paid plans. Pricing is usage-based on simulator minutes, at $0.10 per minute for iOS and Android. The Starter, Production, and Enterprise plans include 60 minutes per month.
Expo will follow Simulators with Agent Sessions, a secure layer that lets enterprises trigger agents from sources such as customer feedback. It protects against prompt injection, where malicious input could direct an agent to expose data. Expo expects to share details by the end of November.
Write to us editorial@demandmediaagency.com. to learn more about our exclusive editorial packages and programmes.
