Skip to main content
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

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 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.

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 and User Management & Permissions.

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 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. Creating a root project Creating a root project

Creating a sub-project

A sub-project creates a filtered view of an existing root 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 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 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 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.