Marketplace / Blueprint 15
COMPOSABLE FROM LIVE SERVICESBusiness Platform / control

AI Platform-as-a-Service

Operate governed AI capabilities for multiple users, teams or customers from one controlled platform.

Review my build
Every building block (identity, workspace, gateway, edge) is live; the packaged multi-tenant commercial workflow is assembled per deployment.

Interactive platform map

Architecture in context

The focused blueprint, its required foundation, and declared recommendations.

Core Selected Automatic Required path
Blueprint 15 / Business Platform

AI Platform-as-a-Service

Operate governed AI capabilities for multiple users, teams or customers from one controlled platform.

2 vCPU5 GB RAM6 services
01 / Problem

What this replaces

Organizations want shared AI but do not want every employee or customer managing separate provider accounts, keys and policies.

02 / Outcome

What your team gains

A multi-user AI service layer with centralized identity, model access, usage controls, shared knowledge and multiple delivery surfaces.

03 / Capability

What is inside the blueprint

SSO and centralized user/group policy
Open WebUI RBAC and per-resource permissions
SCIM user/group provisioning options
LiteLLM virtual keys and per-project/user spend tracking
Budgets/rate limits
Model and provider abstraction
Shared or restricted knowledge bases
API access for apps/bots
Usage analytics and model evaluation
Multiple interfaces: web, Telegram, API, mobile/voice extensions
Foundation for tenant-specific branding and support tiers
04 / Architecture

How it fits the platform

Users/clients -> Authentik -> Open WebUI/API -> LiteLLM -> models + knowledge + tools; Postgres stores tenant/application state.

Included services

Authentik, Open WebUI, LiteLLM, PostgreSQL, Traefik, cloudflared

Platform requirements
05 / Delivery

From prerequisites to operation

Prerequisites
  1. Core platform
  2. User/tenant model
  3. Commercial usage and support policy
  4. Provider/compute capacity
Deployment
  1. Define groups/tenants
  2. Provision SSO and workspace access
  3. Create model keys/budgets
  4. Segment knowledge/tools
  5. Publish tenant-facing routes/APIs
Configuration
  1. Roles/groups
  2. Model permissions
  3. Budgets
  4. Rate limits
  5. Knowledge access
  6. Branding
  7. API key policy
Operations
  1. Provisioning/deprovisioning
  2. Cost allocation
  3. Capacity
  4. Tenant isolation
  5. Support and audit
06 / Combinations

What this unlocks with other layers

AI Platform-as-a-Service + Executive Intelligence & Reporting

Managed AI Business

A provider can sell governed AI access to teams and customers and track usage and cost centrally.

07 / Technology

Technology behind this capability

Open WebUIRUNNING - v0.11.0 in censusLiteLLMRUNNINGPostgreSQLRUNNING - three separate DB instances in censusAuthentikRUNNING - server + worker + DB + RedisTraefikRUNNING - only ingress pathCloudflare TunnelRUNNING