AI Workspaces

An AI Workspace is a scoped AI environment inside a Qefro organization (tenant). Each workspace has its own knowledge base, assistant instructions, Business Tools, and conversations. Customer AI (website widget, WhatsApp) and Employee AI (Internal Portal) bind to workspaces you configure in the Admin Console.

Introduction

In the product data model:

• Organization / tenant — top-level isolation and billing boundary (app.qefro.com signup)
• Workspace — team/use-case boundary (Customer Support, HR, IT, …)
• Team (org RBAC) — grants Members access to specific workspaces

Admin Console APIs expose workspaces under /api/v1/org/workspaces (list/get) and GraphQL for day-to-day console operations.

Why it exists

Mixing customer FAQs with internal HR policy causes inaccurate answers and privacy risk. Workspaces make isolation the default: retrieval and Business Actions stay inside the selected workspace.

Concepts

Term	Meaning in Qefro
Organization	Tenant: users, billing, branding, widget token
Workspace	Isolated knowledge + tools + conversations
Instructions	System guidance (tone, language, refusal)
Business Tools	REST/OpenAPI connectors bound to a workspace
Experience	Widget, Internal Portal, or WhatsApp → workspace

Architecture

Tenant

Organization

Billing, members, branding, publishable widget token.

Scope

Workspace

Knowledge and tools never cross unless you design it.

Access

Teams + RBAC

Owner/Admin/Member; Members only see granted workspaces.

Workflow

Operate a workspace

1. Create — Admin Console → create workspace and name the use case.
2. Ingest knowledge — Upload documents or crawl approved sites (POST /api/v1/documents).
3. Attach tools — Under the workspace, create integrations/tools or import OpenAPI.
4. Bind channels — Widget data-workspace-id, portal workspace access, WhatsApp mapping.
5. Monitor — Analytics, feedbacks, and tool execution logs.

Code examples

Widget bind

<script
  src="https://cdn.qefro.com/widget.js"
  data-token="YOUR_WIDGET_TOKEN"
  data-endpoint="https://api.qefro.com"
  data-workspace-id="YOUR_WORKSPACE_ID">
</script>

Org workspaces API

curl -sS \
  -H "Authorization: Bearer $USER_JWT" \
  https://api.qefro.com/api/v1/org/workspaces

Best practices

• One primary audience per workspace (customers vs employees)
• Start narrow on knowledge quality before bulk imports
• Cross-test: ask Support questions against HR knowledge to prove isolation
• Assign a human owner per workspace

Security notes

Warning

Do not attach privileged write Business Tools to a public Customer AI workspace without identity forwarding (identify()) and least-privilege scopes.

FAQ

What is an AI Workspace?

A scoped AI environment with its own knowledge, instructions, Business Tools, and conversations inside a Qefro organization.

How do Members get access?

Via Organization → Teams: add users to a team, then attach workspaces to that team. Owners/Admins can access all workspaces.

Related topics