Portal overview

Sign in to the Portal, choose a workspace, and set your language and appearance.

Agentic Friendly

The Portal is the main user interface of BullSequana AI. It gives business users, AI engineers, and platform teams a single web surface for AI tasks, model management, data workflows, and administration.

Access to features depends on the roles and permissions granted in your deployment.

Workspace overview

After authentication, the Portal opens OmniChat. Use the workspace switcher at the top of the sidebar to move between workspaces. Opening a workspace does not grant access to every feature or resource within it.

WorkspaceUse it for
OmniChatConversations, files, Agents, Skills, research, voice, connected tools, and Build chats.
StudioModels, deployment, model templates, the Data Catalog, data ingestion, and Spark compute.
AdministrationTenant lifecycle and tenant-wide configuration. Shown only to those who can enter it.
DocumentationThe documentation site, in a separate browser tab.

The account menu at the bottom of the sidebar holds Organization, Language, Theme, API Keys, My usage, and Log out. My usage shows your own model and API usage; see Review your usage. API Keys creates keys for the BSQAI API.

Studio

Studio brings model, data, and compute work into one workspace. Its sidebar has these groups:

GroupPagesGuide
ModelsAvailable models, Model repository, ExperimentsModels in Studio
DeploymentDeploy a model, Download model, and, in the Global organization, Model routingModels in Studio
TemplatesModel presets, vLLM recipes catalogueModels in Studio
DiscoverData CatalogData catalog
Data IngestionOverview, Connectors, Connections, Ingestions, RunsData ingestion in Studio
ComputeClusters, JobsSpark

Studio opens on Available models. Each page has its own permission check, and pages that depend on the organization's private MLflow show a notice until it is ready. Changing the active organization returns Studio to its start page, or to the start of the data or compute area you are in.

Homepage

The BullSequana AI homepage is the sign-in entry point for the portal. Its heading reads Sign in to your workspace, and users select Sign in to authenticate through the shared SSO experience.

On wide screens, the service catalog shows beside the sign-in. It groups the user-facing services exposed in the current environment under Platform, AI, Data, Workflows, Observability, Platform Administration, and Resources. The portal filters and deduplicates backend routes before presenting them in the catalog.

When the deployment exposes a Lakekeeper route, the Data group includes Lakekeeper, opening its catalog interface. Its own access controls still apply; see the lakehouse Data Catalog.

This service list is environment-specific and backend-driven, so the exact entries can differ from one deployment to another.

In practice, this page acts as a service directory for the platform: once users authenticate through SSO, they can access the services they are entitled to use, subject to the access rights and authorization rules configured in the deployment.

Sign-in flow

For most users, access works as follows:

  1. Open the BullSequana AI URL supplied for the deployment.
  2. Select Sign in.
  3. Authenticate with the configured enterprise identity provider.
  4. Return to the portal with the roles and Keycloak Organization memberships assigned to the account.

The same SSO session is used across supported platform services. A deployment can federate Keycloak with Microsoft Entra ID, LDAP, Active Directory, another Keycloak instance, or another supported identity provider.

Organizations and tenants

An organization represents your tenant in BullSequana AI. The selected tenant determines which conversations, resources, and settings you work with.

Users who belong to one organization enter that tenant automatically. Users who belong to more than one organization select the active organization in the portal. Changing it reloads tenant-scoped data so records cached for the previous tenant are not shown in the new context.

The active tenant applies to:

  • chats and responses
  • files, folders, and RAG selections
  • Agents and Connectors
  • API keys and model presets
  • MLflow experiments and registered models in Studio
  • configuration, branding, translations, and web-search providers

Studio uses the MLflow of the active organization. The Global organization uses the installation's MLflow, and a customer organization uses its own private MLflow when an administrator has enabled it. Without a ready private MLflow, Studio shows a notice instead of another organization's content. See MLflow follows the active organization.

Selecting a tenant does not grant access to every resource within it. Membership, assigned roles, and resource sharing determine your access.

Ask your tenant administrator to check membership and roles when an expected workspace or action is unavailable. For identity-provider setup or additional authentication steps, use Enterprise sign-in.

What the portal is for

Use the portal when you want to:

  • chat with available AI models
  • upload and manage files
  • check which models are available in your environment
  • manage reusable assistants
  • configure data connections and operate ingestions in Studio
  • run Spark clusters and PySpark jobs in Studio
  • configure selected AI and platform settings
  • review your own model and API usage

Languages and appearance

The account menu at the bottom of the sidebar holds the language and theme controls.

Languages

Language in the account menu offers these languages:

  • English
  • Français
  • Deutsch
  • Svenska

Changing the language updates the active locale route and reloads the portal in the selected language.

Light and dark mode

Theme in the same menu offers:

  • Light
  • Dark
  • System

Choose a fixed theme or follow the system preference of your device.

On this page