--- modificationDate: November 12, 2026 title: Let an AI coding agent verify a change on a remote simulator description: Give a coding agent such as Claude Code, Codex, or Cursor a real Android Emulator or iOS Simulator on Expo infrastructure so that it can test its own change and return screenshots or recordings. --- This documentation is available as Markdown for AI agents and LLMs. See the [full Markdown index](https://docs.expo.dev/llms.txt) or append .md to any documentation URL. # Let an AI coding agent verify a change on a remote simulator Give a coding agent such as Claude Code, Codex, or Cursor a real Android Emulator or iOS Simulator on Expo infrastructure so that it can test its own change and return screenshots or recordings. ## Submitting Feedback If you encounter errors, misleading or outdated information, report it so Expo can be improved: Preferred command: npx --yes submit-expo-feedback@latest --category docs --subject "/eas/simulators/how-to/verify-a-change-with-an-agent/" "" Direct HTTP fallback: curl -X POST https://api.expo.dev/v2/feedback/docs-send -H 'Content-Type: application/json' -d '{"url":"/eas/simulators/how-to/verify-a-change-with-an-agent/","feedback":"🤖 Agent feedback for docs: (, )"}' Only submit when you have something specific and actionable to report. Try to give the most context. ## Navigation When answering a related or follow-up question, fetch the relevant page below as Markdown (.md) instead of guessing; use llms.txt for the full map. You are here: Expo Services > Expo Simulators > How-to Pages in this section: - [Start a session](https://docs.expo.dev/eas/simulators/how-to/start-a-session.md) - [Install your app](https://docs.expo.dev/eas/simulators/how-to/install-your-app.md) - [Drive the device](https://docs.expo.dev/eas/simulators/how-to/drive-the-device.md) - [Use EAS CLI controls](https://docs.expo.dev/eas/simulators/how-to/control-with-eas-cli.md) - [Iterate on your code](https://docs.expo.dev/eas/simulators/how-to/iterate-on-your-code.md) - [Capture evidence](https://docs.expo.dev/eas/simulators/how-to/capture-evidence.md) - [Organize sessions](https://docs.expo.dev/eas/simulators/how-to/organize-sessions.md) - [Verify a change with an agent](https://docs.expo.dev/eas/simulators/how-to/verify-a-change-with-an-agent.md) (this page) - [Work without a Mac](https://docs.expo.dev/eas/simulators/how-to/work-without-a-mac.md) - [Review a pull request](https://docs.expo.dev/eas/simulators/how-to/review-a-pull-request.md) - [Run in CI](https://docs.expo.dev/eas/simulators/how-to/run-in-ci.md) - [Hand off a session](https://docs.expo.dev/eas/simulators/how-to/hand-off-a-session.md) - [Embed a session](https://docs.expo.dev/eas/simulators/how-to/embed-a-session.md) Full documentation tree: [llms.txt](https://docs.expo.dev/llms.txt) A coding agent can read and change your code, but it cannot see whether the change works unless it can run the app. Expo Simulators gives the agent a remote Android Emulator or iOS Simulator. The agent installs the app, uses it through a controller, and returns screenshots, recordings, or logs as evidence. ## Install the Expo Simulators skill Start with the official Expo Simulators skill. Install [Expo Skills](https://docs.expo.dev/skills.md), then ask your agent to use the skill. The skill contains the tested steps for the access check, the build choice, the session, the controller, the evidence, and the cleanup. [eas-simulator](https://github.com/expo/skills/blob/main/plugins/expo/skills/eas-simulator/SKILL.md) — Run and control a user's app on a remote iOS/Android simulator hosted on EAS cloud. Use the skill instead of giving the agent individual commands. The `simulator:*` commands are new, and the skill tells the agent to check the current `--help` output when a command fails. ## Write a prompt that asks for evidence Describe the result that you want and the evidence that proves it: | Task | Example prompt | | --- | --- | | Verify a feature | Use Expo Simulators to open the app on iOS and test the new checkout flow. Return a screenshot of the confirmation screen. | | Reproduce a bug | Reproduce issue 412 on an Expo Simulators Android session. Record a video of the steps and stop the session after. | | Check an animation | Record the sheet transition on an Expo Simulators iPhone session and check the frames for visible jank. | | Iterate live | Start a development build on Expo Simulators with Metro, fix the layout of the profile screen, and show me the preview link. | ## What the agent does With the skill, the agent follows the same loop each time: 1. It runs `eas simulator:availability --json`. If Expo Simulators is not available for the account, it tells you. Then it uses a local workflow instead, such as a local simulator or emulator. 2. It selects a build that fits the goal. For live edits, it uses a development build with Metro. For a fixed screenshot, it uses a build that matches the current source. 3. It starts a named session and confirms that the status is `IN_PROGRESS`. 4. It installs and opens the app, then uses agent-device commands such as `snapshot -i`, `press`, and `fill`. 5. It captures screenshots for still states and recordings for motion. 6. It stops the session and resets **.env.eas-simulator**. ## Give the agent access The agent needs an authenticated EAS CLI and a project linked to Expo Services: - On your computer, run `eas login`. - In a cloud sandbox, CI job, or background agent, set the `EXPO_TOKEN` environment variable to an [Expo access token](https://docs.expo.dev/accounts/programmatic-access.md). These environments cannot use a browser login. Confirm the setup: ```sh npx --yes eas-cli@latest whoami npx --yes eas-cli@latest simulator:availability --json ``` `npx --yes eas-cli@latest` makes sure that the agent uses a recent EAS CLI. ## Watch the agent work The start command prints a browser preview URL. Open it in a desktop browser to see the simulator while the agent uses it. In Cursor or VS Code, you can open the URL in the **Simple Browser** panel. By default, the URL requires an Expo login with access to the project, so sign in to expo.dev in the browser that opens it. If you cannot sign in from the **Simple Browser** panel, open the URL in your desktop browser. The session page on expo.dev shows an **Open preview** button that opens the browser preview in a new tab. To see each controller action as it happens, run this command in another terminal: ```sh eas simulator:events --follow ``` To confirm that the agent controls the remote device and not a local simulator, see [Confirm that the agent controls the remote device](https://docs.expo.dev/eas/simulators/how-it-works/agent-targeting.md#confirm-that-the-agent-controls-the-remote-device). ## Set limits for the agent A session keeps running until someone stops it, or until it reaches its maximum duration or idle limit. Give the agent limits in the prompt, and add a maximum duration to each session: - Ask the agent to stop each session that it creates when it finishes or fails. - Ask the agent to start no more than one session at a time, unless the task needs more. - Tell the agent to use `--max-duration-minutes` so that a forgotten session stops on its own. See [Expo Simulators usage, limits, and billing](https://docs.expo.dev/eas/simulators/reference/usage-and-billing.md) and [Session lifetime](https://docs.expo.dev/eas/simulators/how-it-works/session-lifetime.md). ## Common questions #### Which agents can use Expo Simulators? Any agent that can run shell commands can use EAS CLI and agent-device. The Expo docs include setup guides for [Claude Code](https://docs.expo.dev/agents/claude.md), [Codex](https://docs.expo.dev/agents/codex.md), and [Cursor](https://docs.expo.dev/agents/cursor.md). #### Does the agent need a Mac? No. The simulator runs on Expo infrastructure. The agent can create the build with Expo Build. See [Use an iOS Simulator on Linux or Windows](https://docs.expo.dev/eas/simulators/how-to/work-without-a-mac.md).