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

# Organizations and Projects 

Nebuly uses a hierarchical structure to organize your AI analytics. Every workspace is composed of **Organizations** and **Projects**, allowing you to separate data, manage access, and analyze multiple AI applications from a single platform.This structure is designed for organizations operating multiple AI assistants, copilots, or customer-facing AI products.Access your organizations and projects using the switcher in the top-left corner.

## **Organizations**

An **Organization** is the highest-level container in Nebuly.Organizations provide complete isolation between environments, including data, users, authentication, and configuration. They are typically used to separate:

* Different companies
* Production and development environments
* Business entities requiring complete data isolation

Data never flows between Organizations.

## **Projects**

A **Project** is the primary unit of analysis inside an Organization.Projects contain the interactions, conversations, users, reports, taxonomies, and analytics for a specific AI deployment.Projects can fall into two categories:

* **Employee-facing projects**: AI applications used internally by employees, such as copilots, internal assistants, or support tools.
* **Customer-facing projects**: AI applications used by customers or other external users, such as customer support agents or in-product assistants.

Within each category, organizations typically create separate projects per:

* AI assistant or agent
* Product
* Business unit
* Team, region or market

Projects are where you’ll spend most of your time analyzing AI usage.

### **Root projects**

A **Root Project** stores the actual interaction data.Every conversation ingested belongs to a single root project. Each root project has its own:

* Reports
* Taxonomies & ROI/Proficiency configuration
* Processing pipeline

Root projects are completely independent from one another.

### **Sub-projects**

A **Sub-project** is a filtered view of a root project.Instead of storing duplicate data, a sub-project applies a permanent filter to its parent project while maintaining its own permissions.For example, you could create:

* Customer Support → France
* Customer Support → Germany
* Customer Support → Italy

All three use the same underlying conversations but only expose the relevant subset.Sub-projects are ideal for regional teams, departments, or business units that should only access their own data.

### **Switching organizations & projects**

Use the organization/project switcher to move between organizations and projects.Nebuly remembers the last project you opened and restores it automatically the next time you sign in.

![Image](https://mintcdn.com/nebulyai/tyxr6Gd4zuVUslkl/images/image-49.png?fit=max\&auto=format\&n=tyxr6Gd4zuVUslkl\&q=85\&s=cc50be7c9fb99918ffb7b0539ac3ffb0)

### **Comparing projects**

Reports can compare two projects side by side, allowing you to analyze differences between AI deployments, teams, or regions without rebuilding your [reports.Best](http://reports.Best) practices

* Create one **root project** per AI application.
* Use **sub-projects** to segment the same data by region, department, or business unit.
* Use **Organizations** only when complete isolation of data, users, or configuration is required.

Read more about how to compare projects [**here**](https://docs.nebuly.com/documentation/reports/configure-reports.md).

## **Managing organizations**

### **Creating an organization**

Organizations are typically created during onboarding by your Nebuly administrator or account team. Each organization is completely isolated from every other organization, making it suitable for separating production and development environments, business entities, or customers.

### **Managing organization members**

Organization administrators can invite new members, remove existing users, and assign organization roles. Membership in an Organization does not automatically grant access to every project. Project access is managed independently.

### **Organization settings**

Organization-level settings apply to every project within the Organization. These include:

* Authentication and Single Sign-On (SSO)
* Organization members and roles
* Alerts and notifications
* Organization-wide preferences

For more information, see [**Authentication**](https://docs.nebuly.com/documentation/admin/authentication.md) and [**User Management & Permissions**](https://docs.nebuly.com/documentation/admin/permissions-and-user-management).

## **Managing Projects**

A **Project** is the workspace where conversations are ingested, analyzed, and reported.

### **Creating a project**

Create a **root project** when you want to analyze a new AI application or ingest conversations from a new data [source.As](http://source.As) part of the setup, you’ll choose whether the project is **employee-facing** or **customer-facing**, depending on who uses the AI application. Your selection determines which modules and features are available for the project, and you can change it at any time from the project settings.Each root project stores its own interactions and configuration, including reports, taxonomies, processing settings, ROI configuration, and API keys.Once created, you can start sending interactions to the project using the [**Interaction API**](https://docs.nebuly.com/tracking/api-reference/events/post-events-interaction-with-trace-v2.md).

![Creating a root project](https://mintcdn.com/nebulyai/G04Jo9hLv86JYsPM/images/create-project.png?fit=max\&auto=format\&n=G04Jo9hLv86JYsPM\&q=85\&s=be7fa55781745e9c787b2e7fbc0711ea)

Creating a root project

### **Creating a sub-project**

A sub-project creates a filtered view of an existing root [project.To](http://project.To) create one:

1. Open the parent root project.
2. Apply the global filters that define the subset of data.
3. Click **Save as project**.
4. Enter a project name.
5. Confirm.

The new project inherits the filtered dataset and appears in the project switcher.

![Creating a sub-project](https://mintcdn.com/nebulyai/G04Jo9hLv86JYsPM/images/create-sub-project.png?fit=max\&auto=format\&n=G04Jo9hLv86JYsPM\&q=85\&s=01c92f9ef48c4ab73e36d7a4dd0cf098)

Creating a sub-project

### **Managing project access**

By default, new users may be granted access to all projects in the Organization, but this can be restricted on a per-project basis to maintain focus and [security.To](http://security.To) change which users have access to a specific project, an Admin can open the project’s settings and adjust the access list. Project-level access is governed by **RBAC** and is independent of Organization-level membership. A user can be a member of an Organization without having access to every project inside it.

![Configuring project access for a user](https://mintcdn.com/nebulyai/G04Jo9hLv86JYsPM/images/project-access-configuration.png?fit=max\&auto=format\&n=G04Jo9hLv86JYsPM\&q=85\&s=d50d1975ab9997dd3e326548e49d1ad8)

Selecting the projects a user can access

## **Key Management Features**

Nebuly is designed to securely separate data across organizations and projects.

* **Organizations** provide complete isolation. Each Organization has its own users, authentication (SSO), settings, alerts, and data. Information is never shared across Organizations.
* **Root projects** contain the actual conversation data and have their own analytics configuration, including taxonomies, AI ROI, AI Proficiency, and processing settings.
* **Sub-projects** inherit data from a root project through global filters, allowing different teams to analyze specific subsets of the same data without duplication.
* **Permissions** are managed independently at both the Organization and Project levels using **Role-Based Access Control (RBAC)**. This lets administrators control who can access each project while maintaining centralized organization management.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.