Collaboration

Create Workspace

In the single-tenant version of the system, you can create workspaces to isolate data. This ensures that users in different workspaces can only access their own workspace's data. The system is structured into two hierarchical levels: - Organization Level There is only one Organization within the system, and it can be thought of as a higher-level workspace. Data such as Agents, Knowledge Bases, and Tools are independent from individual workspaces , similar to how workspace data is isolated. However, LLM (Large Language Model) configurations are shared across all workspaces within the same organization. Workspaces do not have independent LLM settings. - Workspace Level Each workspace has independent data for Agents, Knowledge Bases, and Tools. Users in one workspace cannot view or modify another workspace's data. Users at the workspace level do not have the ability to configure the LLM settings and will share the LLM configuration set at the organization level. Scenarios - For Enterprise Use: You can create multiple workspaces to segment different departments of the company. For example, you may create dedicated workspaces for the Marketing team and the Customer Support team, keeping their data isolated. - For Agency Use: Agencies can create separate workspaces for different clients to ensure that each client's data is securely isolated and managed independently. Creating Workspaces To create a workspace, log in as an Organization Admin . Navigate to the Settings menu and go to the Workspace tab. From there, click on “Add Workspace” , then enter the Workspace Name and a brief Description . After you input this information, the new workspace will be created, and ready for use. When you create a new member in the system, you will have the option to assign specific workspace permissions. This allows you to define which workspace(s) the new member can access and modify. Members will only be able to interact with the workspace(s) you assign to them, ensuring data separation across workspaces. For users that have access to multiple workspaces, they can easily switch between them using the left-hand menu. This allows users to freely navigate between different workspaces to access or edit the data associated with each one, without interfering with the data of other workspaces.

Members Management

Inviting New Members Only Administrators are authorized to invite new members to the team. To add a new member, the Administrator should click on "Setting" -> "Member" -> "Invite Member". After entering the member's email address and selecting the appropriate permissions for the new member, the invitation process is complete. The invited individual will receive an email to complete their registration. Member Roles and Permissions - Administrator: Role Description: The Administrator governs the organization or workspace, managing team members and setting model providers. Permissions Overview: Administrators can modify member roles, add or remove both workspaces and members, configure model providers, and manage agents, knowledge bases, tools and workflows. - Member: Role Description: Regular team members engage primarily as contributors with access to resources within the workspace. Permissions Overview: Members are permitted to utilize agents and tools available within the workspace. They can also edit the existing knowledge bases. Removing Members Administrators hold the exclusive right to remove team members. To carry out this process, administrators should go to "Setting" → "Member", locate the particular member to be removed, and click on "Delete Member" to finalize the removal.

Monitering

In the Monitoring section, you have the ability to oversee and assess your agents' effectiveness. The Statistics dashboard provides a robust platform for examining a variety of metrics within the production environment. Key Metrics for Monitoring: Total Messages This metric illustrates the total number of daily messages between users and the AI. Every time AI answers a user's query, it records as one message. Active Users This figure represents the count of unique users who have engaged in meaningful interactions with the AI, denoted by having multiple question-and-answer interactions. Average User Interactions This metric captures the average number of continuous interactions during a single user session. For instance, if a user engages in a 10-round Q&A session with the AI, it is recorded as 10 interactions. This data serves as an indicator of user engagement levels. Token Usage Tracks the daily consumption of tokens for LLM requests, serving as a vital indicator for managing operational costs and resource allocation efficiency.

Alert Setting

TBD