Skip to content
HN On Hacker News ↗

Deltix · Test your mobile app like a real user

▲ 54 points 12 comments by oneounceman 1w ago HN discussion ↗

Pangram verdict · v3.3

We believe that this entire text is AI.

99 %

AI likelihood · overall

AI
0% human-written 100% AI-generated
SEGMENTS · HUMAN 0 of 1
SEGMENTS · AI 1 of 1
WORD COUNT 401
PEAK AI % 99% · §1
Analyzed
Aug 15
backend: pangram/v3.3
Segments scanned
1 windows
avg 401 words each
Distribution
0 / 100%
human / AI fraction
Verdict
AI
Pangram v3.3

Article text · 401 words · 1 segments analyzed

Human AI-generated
§1 AI · 99%

Describe a task in plain English. Deltix runs it on a simulator and tells you if a real user could complete it.Start freeWatch a real runOpen beta · iOS today · No credit cardSEE IT IN ACTIONWatch a real run.Privacy by defaultYour source and your build stay on your Mac.The agent runs locally against your simulator. We never access your source, your build, or your signing identities.Read moreWhile 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.Step 01Sign upFree. No credit card. No invite needed. Verify your email and you’re in.Step 02Install the Mac AgentA small native app. Sign in with the account you just created. That’s the only one-time setup.Step 03Connect a simulatorPick any iOS Simulator already running on your Mac. The Agent attaches to it and stays out of your way.Step 04Run your first taskWrite a task in plain English, like "sign up and send your first message." The agent tries it. You watch it work.TaskTry once“Can my user actually do this?”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.PlaybookSave and replay“Did we break it?”Take any successful run and save it as a Playbook. Replay it deterministically on every build, from the dashboard. Pass or fail in seconds.ExperimentCompare two builds“Which design wins?”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.Task“Sign up with email and verify the welcome screen appears.”Agent exploringStep 1→Step 2→Step 3→Step 4The agent reports each step, what it saw, and what changed.What’s nextOn the way.In ProgressPhysical devicesRun tasks on a real iPhone attached to your Mac.NextAndroidSame Agent, against an Android emulator.NextCLI for CIReplay Playbooks from GitHub Actions, GitLab, or CircleCI.LaterHybrid appsReact Native and Flutter, treated the same as native iOS.Open betaStart free.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.Create your accountAlready signed up? Log in.