Deltix · Test your mobile app like a real userSign in<br>Test your mobile app like a real user.<br>Describe a task in plain English. Deltix runs it on a simulator and tells you if a real user could complete it.<br>Start free→Watch a real run↓Open beta · iOS today · No credit card
SEE IT IN ACTION<br>Watch a real run.<br>Watch "Deltix product demo" on YouTubeWatch
Privacy by default<br>Your source and your build stay on your Mac.<br>The agent runs locally against your simulator. We never access your source, your build, or your signing identities.<br>Read more↓While a run is in progress the agent acts on what it sees on screen, like any user would. Those screenshots and the run record sit in your account so you can review and replay. Delete anytime, or bring your own model key to route inference traffic off our bill.
How it works<br>Four steps to your first run.
Step 01<br>Sign up<br>Free. No credit card. No invite needed. Verify your email and you’re in.
Step 02<br>Install the Mac Agent<br>A small native app. Sign in with the account you just created. That’s the only one-time setup.
Step 03<br>Connect a simulator<br>Pick any iOS Simulator already running on your Mac. The Agent attaches to it and stays out of your way.
Step 04<br>Run your first task<br>Write a task in plain English, like "sign up and send your first message." The agent tries it. You watch it work.
What it does<br>One primitive, three modes.<br>Everything in Deltix is built on a single thing: an AI agent attempting a user task. The three modes are the three ways you run it.
Task<br>Try once<br>“Can my user actually do this?”<br>Ad-hoc. You’re building a new flow and you want to know if it works for a real user, without scheduling a research session. Write the task, watch the agent try, read the screenshot of where it got stuck.
Playbook<br>Save and replay<br>“Did we break it?”<br>Take any successful run and save it as a Playbook. Replay it deterministically on every build, from the dashboard. Pass or fail in seconds.
Experiment<br>Compare two builds<br>“Which design wins?”<br>Run the same task against two builds of your app, side by side. See which one your users can complete and which one breaks, before the design debate goes to A/B testing in production.
How it fits<br>From discovery to regression.<br>Most testing tools force a choice. Deltix does both.
01Explore<br>Describe a task in plain English. Deltix navigates your app like a first-time user, discovering, hesitating, succeeding, or getting stuck. Every step is captured.<br>02Save<br>When a run completes the flow you wanted, save it. One click turns the successful path into a deterministic playbook. Same interactions, same targets, every time.<br>03Replay<br>Replay the playbook from the dashboard against any new build. Same interactions, same checks. Pass or fail in seconds, with no flaky XCUITest assertions to maintain.
Task<br>“Sign up with email and verify the welcome screen appears.”<br>Agent exploring<br>Step 1<br>Step 2<br>Step 3<br>Step 4
The agent reports each step, what it saw, and what changed.
What’s next<br>On the way.<br>●In Progress<br>Physical devices<br>Run tasks on a real iPhone attached to your Mac.
●Next<br>Android<br>Same Agent, against an Android emulator.
●Next<br>CLI for CI<br>Replay Playbooks from GitHub Actions, GitLab, or CircleCI.
○Later<br>Hybrid apps<br>React Native and Flutter, treated the same as native iOS.
Open beta<br>Start free.<br>Run tasks against a simulator on your Mac while we’re in open beta. Bring your own model key or use ours. No credit card. No invite.<br>Create your account→Already signed up? Log in.