AI mobile app testing

# Test your iOS app on a real iPhone with an AI agent

Describe a test in plain English. Your agent runs it on your own iPhone and tells you what broke.

* Tests your real build on your iPhone
* Works with Claude Code, Codex and Cursor
* No test scripts, nothing installed on the phone

[Download for Mac](https://github.com/Zeptap/releases/releases/latest/download/Zeptap.dmg)[See it work ↓](#how-it-works)

First hour free · macOS 14 or later

Install the newest TestFlight build, go through sign-up as a new user and tell me where it breaks.

Your agent · your iPhone testing

Sign-up · TestFlight build 142

1. Install from TestFlight pass
2. Onboarding, 3 screens pass
3. Allow notifications pass
4. Email and password pass
5. Continue to your account fail

Step 5 breaks: Continue does nothing after the password screen. Screenshot attached, and the steps to reproduce.

## How it works

Your agent tests your app the way a person would, on the iPhone on your desk.

1. **Install your build** the way you already do: [TestFlight](https://developer.apple.com/testflight/), the App Store or Xcode. Zeptap doesn’t build or sign your app.
2. **Describe the journey** to Claude Code, Codex, Cursor or Zeptap’s built-in chat, in plain English.
3. **The agent opens the app** and taps, swipes and types through it like a user, while you watch on your Mac.
4. **It tells you what broke and where.** A coding agent can then fix the code and run the step again.

## What your agent can test on a real iPhone

Your agent runs the journeys you’d otherwise check by hand, and reports what it saw at each step.

* ### Test what you just built  
Your coding agent changes a screen, checks it on your iPhone and fixes what doesn’t work. → [Test your Claude Code iOS app on a real iPhone](https://zeptap.com/use-cases/app-testing/claude-code)
* ### Walk through onboarding  
First launch, permission prompts, test-account sign-in. It flags confusing copy, dead buttons and errors.
* ### Reproduce a bug report  
It follows the customer’s steps, stops at the first screen that differs and tells you what it sees.
* ### Smoke-test each build  
Sign in, search, open an item, save it.
* ### Check larger text and Dark Mode  
It changes the setting, looks for clipped text, then puts the setting back.
* ### Capture App Store screenshots  
Every key screen of the real app. → [Capture App Store screenshots with AI](https://zeptap.com/use-cases/app-testing/app-store-screenshots)

## Where AI agent testing fits among mobile app testing tools

Agent testing on your own iPhone covers the exploratory “does this actually work?” pass; scripted frameworks and device clouds still own large regression suites.

| Tool                         | Best for                                           | Runs on                                                                 | Needs                                                |
| ---------------------------- | -------------------------------------------------- | ----------------------------------------------------------------------- | ---------------------------------------------------- |
| XCUITest, Appium, Maestro    | Regression suites in CI                            | Simulators or a device cloud (XCUITest and Appium also on your devices) | Scripts you write and maintain                       |
| Device clouds                | Many iPhone models and iOS versions                | Remote phones                                                           | An uploaded build and a paid plan                    |
| Claude Code’s Simulator pane | Agent checks while you build                       | iOS Simulator only                                                      | Claude Code Desktop, Xcode, a paid Claude plan       |
| **Zeptap**                   | Agent checks with real accounts and system screens | Your own iPhone, cabled to your Mac                                     | The app on the phone, a Zeptap plan and your AI plan |

Anthropic’s docs say the Simulator pane “drives simulated devices only and can’t control a physical iPhone or iPad” ([Anthropic](https://code.claude.com/docs/en/desktop-ios-simulator), checked 14 October 2026).

### What device clouds cost

Device clouds charge per user, parallel test, device or minute. Prices from each vendor’s pricing page, checked 14 October 2026:

| Service                                                               | Cheapest plan                 | Price                                                        | Billing                     |
| --------------------------------------------------------------------- | ----------------------------- | ------------------------------------------------------------ | --------------------------- |
| [BrowserStack](https://www.browserstack.com/pricing?product=app-live) | App Live / App Automate       | $39 / $199 a month                                           | Annual                      |
| [TestMu AI](https://www.testmuai.com/pricing/) (formerly LambdaTest)  | Live / Automation, 1 parallel | $39 / $199 a month                                           | Annual                      |
| [Sauce Labs](https://saucelabs.com/pricing)                           | Live / Real Device Cloud      | $39 / $199 a month                                           | Annual ($49 / $249 monthly) |
| [Maestro Cloud](https://www.maestro.dev/pricing)                      | Cloud                         | $250 per device a month                                      | Monthly                     |
| [AWS Device Farm](https://aws.amazon.com/device-farm/pricing/)        | Metered / Unmetered           | $0.17 per device minute / $250 per slot a month              | Metered / monthly           |
| **Zeptap**                                                            | One iPhone / up to five       | $25 a month or $99 once (one iPhone); $199 once (up to five) | Monthly or one-time         |

Clouds sell coverage of phones you don’t own; Zeptap uses the one you have, signed in.

## What a real iPhone catches that a simulator can’t

A real iPhone runs the build your testers install. On it, your agent can also test:

* TestFlight and App Store builds, which the Simulator can’t install
* Real SMS sign-in codes
* The camera
* Links that hand off to Mail
* Real hardware and a real network

Apple notes that simulators “don’t replicate the performance or features of a physical device” ([Apple, Running your app on simulated or physical devices](https://developer.apple.com/documentation/xcode/running-your-app-on-simulated-or-physical-devices), checked 14 October 2026).

## Prompts to try

Paste one into Zeptap’s chat or your coding agent.

> Open our app as a new user, go through onboarding with the test account, and describe every screen that confused you.

> Sign in, search for “running shoes”, open the first result and save it. Tell me if any step fails or feels slow.

> Follow these steps from a bug report on the test account. Stop at the first screen that doesn’t match what the user expected and tell me what you see.

Show 3 more prompts

> Set text size to the largest setting, open our sign-up and checkout screens, list anything clipped or overlapping, then restore the original size.

> Install the latest TestFlight build, then check that sign-in, the notification prompt and the paywall’s Restore Purchases button all work.

> Open the app on my iPhone, test every toggle on the settings screen you just changed, and fix anything that doesn’t stick after a relaunch.

[The whole prompt library →](https://zeptap.com/use-cases/prompts)

## You stay in control

You watch every tap live on your Mac and can stop the agent at any moment.

* ### Nothing on the iPhone  
No app, no jailbreak, no developer account for testing.
* ### Your passcode never leaves your Mac  
It’s kept on your Mac; the agent never sees it.
* ### Your screen never touches Zeptap’s servers  
Screenshots go only to the AI provider you chose. Use test accounts. [Privacy](https://zeptap.com/docs/reference/privacy)
* ### You set the stopping points  
Tell your agent to check with you before purchases or messages to real contacts, and stop it from your Mac at any time.

### Honest limits

* It works from screenshots and on-screen text, not accessibility labels, so icon-only buttons are tapped by position.
* It runs one action at a time, when you run it. Zeptap has no built-in scheduler.
* The iPhone stays cabled to your Mac: good for checks while you build, not CI or a device matrix.

## Start testing in three steps

1. **Download Zeptap** for your Mac (macOS 14 or later).
2. **Plug in your iPhone and pair it.** Zeptap walks you through it.
3. **Ask your agent.** Press ⌘L for Zeptap’s chat, or connect [Claude Code](https://zeptap.com/agents/claude-code), [Cursor](https://zeptap.com/agents/cursor) or any MCP agent in **Settings › Connectors** ([connection guide](https://zeptap.com/docs/agents/connect)).

**[Download for Mac](https://github.com/Zeptap/releases/releases/latest/download/Zeptap.dmg)**First hour free

## questions?

The [docs](https://zeptap.com/docs) go deeper, and they're written for agents to read too.

How do I use AI for QA testing?

To use AI for QA testing, describe the journey in plain English and let an agent run it. With Zeptap, an agent such as Claude Code, Codex or Cursor taps through your iOS app on your iPhone and reports each failed step. Keep XCUITest or Maestro suites for CI regression.

How can I test my app on a real iPhone?

To test your app on a real iPhone with AI, install your build through TestFlight, the App Store or Xcode, connect the iPhone to Zeptap and ask your agent to run the journey. The agent can also open TestFlight and install your latest build itself.

Can Claude Code test my app on a real iPhone?

Claude Code can test your app on a real iPhone once you connect Zeptap as an MCP server. Its built-in Simulator pane works only with the iOS Simulator, per Anthropic’s docs. [More on Claude Code](https://zeptap.com/use-cases/app-testing/claude-code)

Do I need Xcode or a paid Apple Developer account?

You don’t need Xcode or a paid Apple Developer account to test with Zeptap. You only need a way to put your build on the phone: TestFlight, the App Store or Xcode, where installs on a [free Apple account expire after 7 days](https://developer.apple.com/support/compare-memberships/).

Which iPhones work?

Every iPhone on iOS 15 or later works, including Home-button models like iPhone SE. Your Mac needs macOS 14 or later. Lifetime Plus connects up to five iPhones at once.

How much does Zeptap cost?

Zeptap costs $25 a month or $99 once for one iPhone, or $199 once for up to five iPhones. Your first hour is free; your AI plan stays separate. [See pricing](https://zeptap.com/pricing)

Does it test Android apps?

Zeptap doesn’t test Android apps: it runs on a Mac and controls iPhones only.

## give your agent an iPhone  
to test on.

[Download for Mac](https://github.com/Zeptap/releases/releases/latest/download/Zeptap.dmg)[or read how to set it up](https://zeptap.com/docs/get-started/install)

Works with Claude Code, Claude, Codex, ChatGPT, Cursor, OpenClaw, Hermes and any MCP client.