> For the complete documentation index, see [llms.txt](https://docs.umbraco.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.umbraco.com/ai-in-umbraco/17.latest/management-api/guardrails/create.md).

# Create Guardrail

Creates a new guardrail with rules for evaluating AI inputs and responses.

## Request

```http
POST /umbraco/ai/management/api/v1/guardrails
```

### Request Body

{% code title="Request" %}

```json
{
    "alias": "content-safety",
    "name": "Content Safety Policy",
    "rules": [
        {
            "evaluatorId": "contains",
            "name": "Block competitor mentions",
            "phase": "PostGenerate",
            "action": "Block",
            "config": {
                "searchPattern": "CompetitorBrand",
                "ignoreCase": true
            },
            "sortOrder": 0
        },
        {
            "evaluatorId": "regex",
            "name": "Block SSNs in responses",
            "phase": "PostGenerate",
            "action": "Block",
            "config": {
                "pattern": "\\b\\d{3}-\\d{2}-\\d{4}\\b",
                "ignoreCase": false
            },
            "sortOrder": 1
        }
    ]
}
```

{% endcode %}

### Request Properties

| Property | Type   | Required | Description             |
| -------- | ------ | -------- | ----------------------- |
| `alias`  | string | Yes      | Unique alias (URL-safe) |
| `name`   | string | Yes      | Display name            |
| `rules`  | array  | No       | Collection of rules     |

### Rule Properties

| Property      | Type   | Required | Description                                |
| ------------- | ------ | -------- | ------------------------------------------ |
| `evaluatorId` | string | Yes      | Registered evaluator ID (e.g., "contains") |
| `name`        | string | Yes      | Display name                               |
| `phase`       | string | Yes      | `PreGenerate` or `PostGenerate`            |
| `action`      | string | Yes      | `Block`, `Warn`, or `Redact`               |
| `config`      | object | No       | Evaluator-specific configuration           |
| `sortOrder`   | int    | No       | Evaluation order (default: 0)              |

## Response

### Success

Returns the newly created guardrail's ID (as a string) with a `Location` header pointing to the Get Guardrail endpoint.

{% code title="201 Created" %}

```json
"3fa85f64-5717-4562-b3fc-2c963f66afa6"
```

{% endcode %}

### Validation Error

{% code title="400 Bad Request" %}

```json
{
    "type": "https://tools.ietf.org/html/rfc7231#section-6.5.1",
    "title": "Duplicate alias",
    "status": 400,
    "detail": "A guardrail with this alias already exists."
}
```

{% endcode %}

## Examples

{% code title="cURL" %}

```bash
curl -X POST "https://your-site.com/umbraco/ai/management/api/v1/guardrails" \
  -H "Authorization: Bearer YOUR_ACCESS_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
    "alias": "content-safety",
    "name": "Content Safety Policy",
    "rules": [
      {
        "evaluatorId": "contains",
        "name": "Block competitor mentions",
        "phase": "PostGenerate",
        "action": "Block",
        "config": { "searchPattern": "CompetitorBrand", "ignoreCase": true },
        "sortOrder": 0
      }
    ]
  }'
```

{% endcode %}

{% code title="C#" %}

```csharp
var guardrail = new
{
    alias = "content-safety",
    name = "Content Safety Policy",
    rules = new object[]
    {
        new
        {
            evaluatorId = "contains",
            name = "Block competitor mentions",
            phase = "PostGenerate",
            action = "Block",
            config = new { searchPattern = "CompetitorBrand", ignoreCase = true },
            sortOrder = 0
        }
    }
};

var response = await httpClient.PostAsJsonAsync("/umbraco/ai/management/api/v1/guardrails", guardrail);
```

{% endcode %}


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## 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, and the optional `goal` query parameter:

```
GET https://docs.umbraco.com/ai-in-umbraco/17.latest/management-api/guardrails/create.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

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.