> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.amniscient.com/docs/testing-inference-against-an-ai-model/detect-an-object-with-an-ai-model/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.amniscient.com/_mcp/server.

# How to Detect an Object on the AmniSphere App

### Log In

Log in to your AmniSphere mobile app. You will be taken to a view of your current folders and objects. Tap on the cube icon in the upper right corner.

![](/_fern-img/edd4efa1cfa8df93f1f44956057ed720a90cfb61c0005caf7eb2b1bfd15540e1.webp)

### Select an AI Model

You will be presented with a view of your currently trained AI models. Select the AI model you'd like to use for object detection.

![](/_fern-img/7910e57988a3bdd823799e65b4bf860e22233449c42979ef4fff9d67d2cdf957.webp)

### Take a Photo

You will be taken to a camera view. Ensure that the object you're detecting is part of the training set for the AI model you've selected. Take a photo of your object with the camera.

### Observe Detection Results

After taking a photo, you should see an outline around your detected object with a confidence rating. The better your object capture process, the higher your confidence rating will be during object detection.