Anas Rahman

Finding early traction and validating app ideas usually feels like a guessing game. Most makers rely on broad category trends or gut feelings, which is incredibly risky. The App Store Top Charts are a trap by the time an app is there, you're already too late to the trend.

We realized the key is analyzing micro-signals across millions of data points, but doing that manually takes forever.

So, alongside tracking 2.2 million apps, we just rolled out our MCP (Model Context Protocol) integration. You can now plug AppGazers directly into Claude, ChatGPT, Cursor or Windsurf.

It passed all the tests it could and then broke a piece of functionality that didn t seem to have any test coverage but certainly had manual QA. It was clean code. That was the issue, clean code that was also confident is hard to be suspicious of when compared to code that doesn t look good at all.

Now I have agents document all the things they cannot test before I allow them near anything that s core. Slow process, but no more surprises.

I ve been building Elsewhere, a calm, open-ended flight toy about exploring places that don t exist.

You get a small aircraft, an endless sky, and no mission to complete. The world is generated as you fly: mountains, islands, coastlines, clouds, changing light, and small low-poly landmarks to discover.