> 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/19.latest/management-api/guardrails/evaluators.md).

# List Evaluators

List available guardrail evaluators.

Returns all registered guardrail evaluators with their configuration schemas. Use this endpoint to discover which evaluators are available when creating guardrail rules.

{% hint style="info" %}
Evaluators that need an experimental capability are left out while that capability is disabled. For example, the Decision Safety Judge (`decision-judge`) is only returned when the `Umbraco:AI:Experimental:Decision` feature flag is enabled.
{% endhint %}

## Request

{% code title="Endpoint" %}

```http
GET /umbraco/ai/management/api/v1/guardrail-evaluators
```

{% endcode %}

## Response

### Success

{% code title="200 OK" %}

```json
[
    {
        "id": "contains",
        "name": "Contains",
        "description": "Flags content containing a specific substring.",
        "type": "CodeBased",
        "supportsRedaction": false,
        "configSchema": {
            "fields": [
                {
                    "key": "searchPattern",
                    "label": "Search Pattern",
                    "description": "The substring to search for in the content.",
                    "editorUiAlias": "Umb.PropertyEditorUi.TextBox",
                    "defaultValue": null,
                    "sortOrder": 0,
                    "isRequired": true
                },
                {
                    "key": "ignoreCase",
                    "label": "Ignore Case",
                    "description": "Whether to perform case-insensitive matching.",
                    "editorUiAlias": "Umb.PropertyEditorUi.Toggle",
                    "defaultValue": true,
                    "sortOrder": 1,
                    "isRequired": false
                }
            ]
        }
    },
    {
        "id": "llm-judge",
        "name": "LLM Safety Judge",
        "description": "Uses an AI model to evaluate content for safety and compliance against configurable criteria.",
        "type": "ModelBased",
        "supportsRedaction": false,
        "configSchema": {
            "fields": [
                {
                    "key": "profileId",
                    "label": "Profile",
                    "description": "The AI profile to use for evaluation.",
                    "editorUiAlias": "Umb.PropertyEditorUi.TextBox",
                    "defaultValue": null,
                    "sortOrder": 0,
                    "isRequired": true
                }
            ]
        }
    }
]
```

{% endcode %}

## Response Properties

| Property            | Type    | Description                                                                     |
| ------------------- | ------- | ------------------------------------------------------------------------------- |
| `id`                | string  | Unique evaluator identifier                                                     |
| `name`              | string  | Display name                                                                    |
| `description`       | string  | What the evaluator checks                                                       |
| `type`              | string  | `CodeBased` or `ModelBased`                                                     |
| `supportsRedaction` | boolean | Whether the evaluator supports the `Redact` action                              |
| `configSchema`      | object  | Configuration schema for UI rendering (nullable when no configuration required) |

### Config Schema Field Properties

| Property        | Type    | Description                                       |
| --------------- | ------- | ------------------------------------------------- |
| `key`           | string  | Unique key identifying the setting                |
| `label`         | string  | Display label for the setting                     |
| `description`   | string  | Help text for the setting                         |
| `editorUiAlias` | string  | UI alias of the editor used for the setting       |
| `editorConfig`  | object  | Configuration for the editor                      |
| `defaultValue`  | object  | Default value for the setting                     |
| `sortOrder`     | int     | Sort order of the setting in the UI               |
| `isRequired`    | boolean | Whether the setting must be provided              |
| `group`         | string  | Optional group name for visual grouping in the UI |

## Examples

{% code title="cURL" %}

```bash
curl -X GET "https://your-site.com/umbraco/ai/management/api/v1/guardrail-evaluators" \
  -H "Authorization: Bearer YOUR_ACCESS_TOKEN"
```

{% endcode %}

{% code title="C#" %}

```csharp
var response = await httpClient.GetAsync("/umbraco/ai/management/api/v1/guardrail-evaluators");
var evaluators = await response.Content.ReadFromJsonAsync<GuardrailEvaluatorInfoModel[]>();
```

{% 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 by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.umbraco.com/ai-in-umbraco/19.latest/management-api/guardrails/evaluators.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

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.