Describe a task in plain English, Deltix tests it on a simulator
AI Driven Testing
Deltix is an open beta tool that lets you describe a task in plain English, which it then runs on an iOS simulator to see if a real user could complete it. The agent runs locally on your Mac, keeping your source and build private, and reports each step it takes. You can watch a live run, save successful runs as replayable playbooks for regression testing, or compare two builds side-by-side. Future plans include physical devices, Android, CI integration, and hybrid app support.
The agent runs locally against your simulator. We never access your source, your build, or your signing identities.
- iamcoder18
Just did this locally by giving my AI agent full ADB access to a test phone I have.
It's actually kinda amazing just watching it swipe, open the app launcher, and find issues to fix later.
- alightsoul
at work, an airline via an outsourcing company, the entire qa workflow is automated. we use claude desktop, the ai picks up a user story from azure devops via rest api or mcp, tests it on the app with playwright or claude browser using skills with software specifications for the product the user story will be merged into, then reports bugs and test results via mcp servers and rest apis to azure devops.
alas it needs manual intervention between each of those steps to copy and paste or publish results or comment on bugs because qa is outsourced and the outsourcing company refuses to not have someone do something manually in order to avoid losing revenue on their end.
the outsourcing company charges the client per person so they want to have as many people working as possible and the client, an airline, wants the exact opposite. they only hire software development students for the job so we are entirely able to fully automate the workflow and replace ourselves. people from the airline are too busy to do it themselves.
I am very sure most companies will just cobble together something with Claude and some skill.
- pluto_modadic
Some assembly required.