Skip to main content
A workspace is an isolated AI execution environment for a team or project. Each workspace has its own connections, knowledge, guardrails, consumers, and audit trail. Data never leaks between workspaces.

What a workspace contains

ResourcePurpose
ConnectionsMCP servers, REST APIs, databases the AI can call
KnowledgeDocuments, pages, and text for context
GuardrailsPII filtering, cost caps, rate limits
ConsumersEntry points: Slack channels, API keys, WhatsApp numbers
PermissionsRole-based tool access patterns

Configuration

Each workspace has:
  • Name: display name in the dashboard
  • Team: the team that owns this workspace
  • Model: the language model tier to use (e.g. balanced, powerful)
  • System prompt: instructions the AI follows for every query
  • Max tool rounds: how many tool-call loops the agent can run (default: 10)
  • Cold timeout: minutes of inactivity before a conversation goes cold
  • Close timeout: minutes after going cold before a conversation is closed

Lifecycle

Workspaces have three statuses:
StatusMeaning
activeNormal operation. Queries are processed, consumers are live.
pausedQueries are rejected. Consumers stop listening. Data is preserved.
archivedRead-only. Historical data accessible but no new queries.

Isolation guarantees

  • Data isolation: conversations, audit logs, and costs are scoped to a single workspace
  • Tool isolation: each workspace discovers tools from its own connections only
  • Consumer isolation: a Slack channel can only belong to one workspace
  • Knowledge isolation: documents are indexed per workspace
  • Compliance isolation: guardrails are set per workspace (org-level baseline cannot be weakened)

Stats

The workspace dashboard tracks:
  • Queries today, this week, this month
  • Cost month-to-date
  • Average response time
  • Error rate
  • Connection count and tool count