> For the complete documentation index, see [llms.txt](https://docs.toucanai.cloud/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.toucanai.cloud/govern/security-model/data-access-boundaries.md).

# Data access boundaries

{% hint style="info" %}
**Target Audience**: Developers & non-technical users defining how Toucan AI accesses data in multi-tenant products.
{% endhint %}

### TL;DR

Toucan AI separates **platform data** (stored in Toucan) from **your business data** (stored in your connected databases). Access to your data is always gated by authentication, permissions, and row-level security — not by copying your warehouse into Toucan.

***

### When to use this

Use this page with [Security boundaries (embed)](/embed/embedding-overview/security-boundaries.md) to design a secure integration and understand shared responsibilities.

***

### Three data zones

| Zone                     | What it is                                                                | Where it lives                                 |
| ------------------------ | ------------------------------------------------------------------------- | ---------------------------------------------- |
| **Platform**             | Accounts, dashboards, chart configs, AI history, encrypted DB credentials | Toucan AI database                             |
| **Your database**        | Tables and rows (source of truth)                                         | Your infrastructure                            |
| **Request-time results** | Rows returned for a chart or AI answer                                    | Processed per request — not a bulk Toucan copy |

See [Data storage & retention](/govern/security-model/data-storage-and-retention.md) for query flow and caching.

***

### How access is enforced

* **Embed tokens** carry identity, permissions, and attributes for security rules (all database configuration can be passed as attributes).
* **Row-level security (RLS)** filters which rows each user can query.
* [**Column-level security (CLS)**](/build/security-and-governance/column-level-security-cls.md) can restrict which columns are visible.
* **Organization isolation** separates one customer’s Toucan configuration from another’s.

***

### Security responsibilities

| Responsibility                     | Your app / backend | Toucan AI platform |
| ---------------------------------- | :----------------: | :----------------: |
| End-user authentication            |          ✅         |          —         |
| Embed token generation             |          ✅         |          —         |
| API key storage                    |          ✅         |          —         |
| Define RLS attributes & rules      |          ✅         |          —         |
| Enforce RLS at query time          |          —         |          ✅         |
| Store platform config & AI history |          —         |          ✅         |
| Store your table data              |     ✅ (your DB)    |  — (queries only)  |

***

### Typical risks

* Missing RLS on sensitive tables
* Sensitive content in AI chat that gets stored in conversation history

***

### Related pages

* [Token security](/govern/security-model/token-security.md)
* [API security](https://github.com/ToucanToco/toucan-ai/blob/main/docs/govern/security-model/api-security.md)
* [Data storage & retention](/govern/security-model/data-storage-and-retention.md)
* [PII & personal data](/govern/security-model/pii-and-personal-data.md)
* [Third-party subprocessors](/govern/security-model/third-party-subprocessors.md)