> ## Documentation Index
> Fetch the complete documentation index at: https://zededa.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

> ## Agent Instructions
> Use the documentation index to find relevant pages, then read the linked Markdown before answering and cite the source URL.
> Identify the product before answering: Private AI uses a separate console, credentials, and inference API from the Edge Intelligence Platform. Do not apply instructions from one product to the other.
> Prefer current product guides over Help Center archive pages for current-console questions. Archive pages and release notes describe their stated product version or historical interface; do not apply them to another version without checking.
> Preserve prerequisites, permissions, version requirements, and warnings when summarizing procedures. Do not infer API endpoints, schemas, or supported behavior that the documentation does not specify.

# Delivery and Deployments Overview

> Learn how to deploy application instances to nodes, automate fleet rollouts with Application Profiles, and follow the application deployment lifecycle.

## Introduction

The Applications and delivery section of Edge Infrastructure Services is where you manage the full deployment lifecycle for edge applications. From this area, you deploy application instances to individual nodes or to a fleet, automate rollouts using Application Profiles, manage running applications, and monitor deployment activity.

### Prerequisites

* You have the SysManager or SysAdmin role in your enterprise. See [Manage Roles](https://zededa.mintlify.site/new-ui/infrastructure-services/administration/manage-roles.md).
* At least one node onboarded to Edge Infrastructure Services.
* At least one application image added to Build and Library.

## How It Works

Every application that runs on a node starts as an application image in your Build and Library catalog. When you deploy an image to a node, Edge Infrastructure Services creates an application instance on that node. You can deploy instances one at a time or in bulk across multiple nodes.

For fleets that require consistent application configuration across many nodes, Application Profiles let you define a deployment specification once and apply it automatically. When a node joins a project or its profile assignment changes, Edge Infrastructure Services applies the matching profile and deploys or updates the configured applications without further manual steps. This is the recommended approach for zero-touch deployment scenarios where new nodes should receive applications automatically.

The deployment lifecycle for an application instance moves through several states: Downloading (the image is being fetched), Starting, Running, and Stopped. You can start, stop, restart, and delete instances from the application operations controls.

## Key Deployment Workflows

**Deploy a single application instance.** Deploy one application image to a specific node. Use this for targeted rollouts, testing, or one-off deployments. See [Deploy an Application Instance](https://zededa.mintlify.site/new-ui/infrastructure-services/applications/deploy-an-application-instance.md).

**Automate deployment with Application Profiles.** Define a profile that specifies which applications deploy to nodes in a project, and Edge Infrastructure Services applies it automatically. This replaces manual per-node deployment for standard fleet configurations. See [Automate Deployments with Application Profiles](https://zededa.mintlify.site/new-ui/infrastructure-services/applications/automate-deployments-with-application-profiles.md).

**Deploy to a fleet.** Roll out an AI application across multiple nodes in a project simultaneously. See [Deploy AI Applications to a Fleet](https://zededa.mintlify.site/new-ui/infrastructure-services/applications/deploy-ai-applications-to-a-fleet.md).

**Submit an AI model deployment request.** Deploy an AI model to a Kubernetes cluster or cluster group through a GitOps-based approval pipeline. Each request routes through a pull request review before the model is deployed. See [Submit Model Deployment Requests](https://zededa.mintlify.site/new-ui/edge-inference-services/submit-model-deployment-requests.md).

**Docker Compose deployments.** Run multi-container applications using the Compose Runtime. See [Deploy the Compose Runtime Application](https://zededa.mintlify.site/new-ui/infrastructure-services/applications/deploy-compose-runtime.md).

## Next Steps

> [card] [Deploy an Application Instance](https://zededa.mintlify.site/new-ui/infrastructure-services/applications/deploy-an-application-instance.md)
>
> Step-by-step deployment instructions.

> [card] [Automate Deployments with Application Profiles](https://zededa.mintlify.site/new-ui/infrastructure-services/applications/automate-deployments-with-application-profiles.md)
>
> Zero-touch fleet deployment setup.

> [card] [Application Operations](https://zededa.mintlify.site/new-ui/infrastructure-services/applications/manage-an-application-instance.md)
>
> Managing the lifecycle of running application instances.

> [card] [Build and Library Overview](https://zededa.mintlify.site/new-ui/infrastructure-services/build-and-library.md)
>
> Adding application images before deploying.