# Multi-tenancy

Stratix is multi-tenant. Each tenant is an **organization** (`org_id`). Every record is scoped to exactly one org. A user can belong to many orgs and switch between them.

## What's per-org

* Private models (BYOK)
* Private benchmarks
* Private evaluations
* Judges and scorers
* Traces and trace evaluations
* Spaces
* Settings, integrations, API keys
* ECU balance and billing
* Audit log

## What's global

* Public catalog (models, benchmarks, public evaluations, public spaces)
* Quarterly research reports
* Learning Library

## Isolation

* **Database** — every record carries `org_id`; row-level security enforces the boundary
* **Cache** — cache keys include `org_id`
* **Queues** — per-tenant streams; one tenant's burst can't affect another
* **API** — auth middleware resolves `org_id` from the API key or session

## Active org

A user with multiple-org membership has exactly one **active org** at a time. Switching orgs in the UI updates the session and refreshes catalog views, dashboards, and Settings.

## Data deletion

When you remove a member, their evaluations, judges, and traces remain in the org (they were org-owned). When you delete an org, all org-scoped data is deleted.

## Enterprise: data residency

Enterprise tier supports per-org data residency selection (US, EU, others). Region selection is per-org, not per-user.

## Where to next

* [Stratix Premium — Organizations](https://github.com/LayerLens/gitbook-full/blob/main/13-reference/sdk-python/organizations.md)
* [Stratix Premium — Team management](/11.-admin/team-management.md)
* [Enterprise](https://github.com/LayerLens/gitbook-full/blob/main/assets/screenshots/README.md)
* [Security and compliance](https://github.com/LayerLens/gitbook-full/blob/main/assets/screenshots/README.md)


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.layerlens.ai/7.-observe-see-whats-happening/multi-tenancy.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.