Projects & Roles

​

Literal AI Projects

You can have multiple projects in Literal AI, each with its own set of members, roles, and settings. Projects are the primary way to organize your work and collaborate with your team.

​

Project settings

Project-level settings in Literal AI:

• LLM Provider Credentials: Manage credentials for the language models used in your project.
• Tags: Customize and manage tags to categorize and label your data.
• Score Schemas: Define and manage scoring schemas to consistently evaluate and measure your AI models’ performance.

​

Create & Invite Members to a Project

To create a new project, click on the Project switcher at the bottom of the sidebar and click on Create Project.

Once a project is created, you can invite others to collaborate:

1. Go to the project Settings.
2. Go to the Team tab.
3. Click on the + button.

​

Role Based Access Control (RBAC)

Project administrators hold the responsibility of assigning and managing permissions for all team members. Permissions in Literal AI are packaged as the following set of roles :

​

Supported roles

• Admin: Full access to the project, including team management, project settings, and all resources.
• AI Engineer: Manages observability data, API keys, and AI prompts. Cannot alter project settings or team roles.
• Domain Expert: Reads observability data, scores, and tags data. Limited access to project resources and no API key or project settings management.

Feel free to reach out to us to create a custom role: contact@literalai.com

​

Permissions per role

​

Manage Literal AI API Keys

To copy or create a new API key, go to the Settings page and look for the Literal AI API Keys section.

Each API key is associated with a specific project, user and role.