Cloud Quick Start

This guide walks you through the end-to-end workflow: from logging into the Nx AI Cloud admin interface to having an AI model running on your edge device. Each step links to the relevant detailed documentation.

circle-info

Before you begin: make sure you have the Nx AI Manager plugin installed on your server and at least one camera device connected.


Step 1: Log into the Nx AI Cloud

Open the Nx AI Cloud admin interface in your browser. Log in with your Nx account credentials.

The Nx AI Cloud admin interface login screen
The Nx AI Cloud admin interface; appearance varies by product variant

Step 2: View your connected sites

After logging in, the Sites page lists all sites registered to your account, with their online/offline status.

Nx AI Cloud sites listing page showing only online sites with green status indicators
     and a Show Offline toggle
Sites listing: all shown sites are online and ready to manage.

Click an online site (green indicator) to open it.

Deployment and device managementchevron-right

Step 3: Find your device

Inside a site, the Devices tab lists all cameras and devices. Each device shows its currently assigned model pipeline.

A site's device list showing three cameras with their assigned model pipelines and
     Clone This Pipeline buttons
Site devices: each device shows its current pipeline. Click Pipelines to open the device detail page.

Click a device to open its detail page.


Step 4: Assign a model pipeline to your device

On the device detail page, click Pipelines to manage the model pipelines running on that device. Use Add a new pipeline to assign a model, or the replace button to swap the existing one.

Device detail page showing the current model pipeline with Add A New Pipeline, Switch,
     Remove, and Add Chained Model buttons, plus sensitivity and postprocessor controls
Device pipeline: use Add A New Pipeline or Switch to assign or replace a model.

The model is downloaded to the device automatically after assignment.


Step 5: Browse available models

From the sidebar, the Models page shows all AI models available to your account: pre-built models from the catalogue and any custom models you have uploaded.

The model catalogue listing page showing available AI models with their descriptions and runtime compatibility
Model catalogue: browse and search available models
Use your modelchevron-right

Step 6: Verify deployment

After assigning, the device detail page confirms the deployment status. The device should begin running inference within a few seconds.

The model detail page showing model information and the list of devices it is currently deployed to
Model detail: confirm the model is deployed to the correct devices
circle-check

What's next?

Last updated