@sharminsirajudeen

Claude + Mobile via MCP: Giving the Model Hands on a Real Phone

May 3 · 5 min read · Claude + Mobile via MCP: Giving the Model Hands on a Real Phone I plugged in a Pixel two months ago, ran one command in Claude Desktop, and watched it open Maps and start navigation to my home address from a single sentence prompt. It was the first t...

AI-Native Mobile Testing: What It Actually Means in 2026

May 3 · 4 min read · AI-Native Mobile Testing: What It Actually Means in 2026 The phrase "AI-native" has been thrown around in the testing space since 2019. Almost every tool calling itself that just bolts a language model on top of Appium and ships the same brittle XPat...

The Missing Control Plane for Local AI Agents

May 3 · 4 min read · The Missing Control Plane for Local AI Agents I sat with my Pixel for 20 minutes trying to get Claude Desktop to dictate a Slack message via accessibility. It was miserable. The model was capable. The transport wasn't. That gap — between an AI that c...

How a Web Worker Fixed My Dying-Battery Audio (And What I Learned About PWAs the Hard Way)

Apr 13 · 8 min read · I spent the last week modifying an open-source NES emulator to run in the browser as a PWA. I'm an Android developer by trade — Kotlin, Jetpack Compose, Flutter when the project calls for it. This was my first real dive into Web Workers, SharedArrayB...

From ADB Shell to AI Agent: The Quiet Revolution in Mobile Automation

Apr 6 · 6 min read · From ADB Shell to AI Agent: The Quiet Revolution in Mobile Automation I'm the creator of Drengr, an MCP server that gives AI agents eyes and hands on mobile devices. I started this blog to share the engineering behind it. No pretending to be a neutr...