Tag
Google has open-sourced ARTEMIS, enabling AI to perform natural language-driven cross-app automation testing on a real Android phone just like a human. It achieves a 99%+ task completion rate on the AndroidWorld benchmark and natively supports MCP, allowing IDEs like Claude Code, Windsurf, and Antigravity to drive devices directly.
The author built CosmoRemote, a tool using a bridge daemon and mobile app to remotely build, run, and test code on Mac simulators from a phone, solving the gap in verifying AI agent work while away.
This article describes how Gemini 3.7 Flash, a hybrid reasoning model, enables interactive Android control through Python scripts by analyzing screenshots and executing precise actions, demonstrated via Wordle game automation.
Kane CLI lets developers run natural language browser and mobile app tests directly from the terminal.
A new tool claimed to enable writing and running automated UI tests for web pages (and iOS/Android apps) 100x faster.
A developer created a way for AI agents to control real iPhones via API, enabling tasks like drafting iMessages, running iOS Shortcuts, and mobile app testing. They are offering access to 70 phones for experimentation.
TesterArmy is a QA tool to test websites and mobile apps across browsers and devices, catching regressions and generating tests from natural language.
A founder shares how a cold DM led to Drizz's first customer, and announces the launch of Drizz, a vision AI agent for mobile app testing, on Product Hunt.
Drizz, an AI agent for mobile/web app testing that uses plain English and visual understanding, is launching on Product Hunt after securing 14 pilot customers through cold outreach and referrals.
A developer connected Claude Code to an iPhone simulator and prompted it to 'test everything,' resulting in autonomous navigation, bug detection, and structured reporting, showcasing a shift from traditional test scripts to AI-driven intent-based testing.
Drizz is a mobile testing tool that autonomously writes, runs, and fixes tests.
TesterArmy open-sourced e2e, an AI-driven end-to-end testing framework where you describe test goals in natural language and an agent drives web or mobile apps via Playwright or device emulators, with actions replayed deterministically on subsequent runs to avoid extra model calls.