Finding bugs with an automated AI test agent

Every day I'm surprised by how capable AI agents are becoming. Today's surprise was how the agent can build its own test-harness to find bugs.

I was reading about MobAI, an online service which tests mobile apps by interacting with them while they're running inside a simulator, like iOS Simulator (part of Xcode).

It occurred to me that this would be a straightforward skill to build in Claude Code.

So I asked Claude to write a skill, which then found issues in my push10k exercise app:

• incorrectly pluralized numbers ("1 weeks")
• year printed with commas (2,026 instead of 2026)
• percentage value rendered incorrectly on status display
• accessibility labels active on inactive tabs
• missing accessibility labels
• incorrectly displayed date

Here's the AppTestCircuit skill, open source MIT license.

And a shout-out to the creators of iosef, the MCP server that AppTestCircuit uses that does all the heavy lifting.