> 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/add-ons/prompt/api/create.md).

# Create

Create a new prompt.

Creates a new prompt template.

## Request

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

### Request Body

{% code title="Request" %}

```json
{
    "alias": "meta-description",
    "name": "Generate Meta Description",
    "description": "Creates SEO-friendly meta descriptions",
    "instructions": "Write a meta description for:\n\nTitle: {{pageTitle}}\nContent: {{bodyText}}\n\nRequirements:\n- Maximum 155 characters\n- Be compelling",
    "profileId": "d290f1ee-6c54-4b01-90e6-d701748f0851",
    "contextIds": ["e401f2ff-7d65-5c12-a1f7-e812859a1962"],
    "guardrailIds": [],
    "tags": ["seo", "content"],
    "includeEntityContext": true,
    "optionCount": 1,
    "displayMode": "PropertyAction",
    "scope": {
        "allowRules": [
            {
                "contentTypeAliases": ["article", "blogPost"]
            }
        ],
        "denyRules": []
    }
}
```

{% endcode %}

### Request Properties

| Property               | Type      | Required | Description                                                                     |
| ---------------------- | --------- | -------- | ------------------------------------------------------------------------------- |
| `alias`                | string    | Yes      | Unique alias (letters, numbers, hyphens and underscores only, max 100)          |
| `name`                 | string    | Yes      | Display name (max 255)                                                          |
| `instructions`         | string    | Yes      | Prompt template text                                                            |
| `description`          | string    | No       | Optional description (max 1000)                                                 |
| `profileId`            | guid      | No       | Associated AI profile                                                           |
| `contextIds`           | guid\[]   | No       | AI Contexts to inject                                                           |
| `guardrailIds`         | guid\[]   | No       | Guardrails evaluated during execution                                           |
| `tags`                 | string\[] | No       | Organization tags                                                               |
| `includeEntityContext` | bool      | No       | Include entity in system message (default: `true`)                              |
| `optionCount`          | int       | No       | Number of result options: 0 = informational, 1 = single (default), 2+ = options |
| `displayMode`          | string    | No       | `PropertyAction` (default) or `TipTapTool`                                      |
| `scope`                | object    | No       | Scope rules (allow/deny) defining where the prompt can run                      |

## Response

### Success

{% code title="201 Created" %}

```
"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": "One or more validation errors occurred.",
    "status": 400,
    "errors": {
        "Alias": ["Alias must contain only letters, numbers, hyphens, and underscores."]
    }
}
```

{% endcode %}

### Duplicate Alias

{% code title="409 Conflict" %}

```json
{
    "type": "https://tools.ietf.org/html/rfc7231#section-6.5.8",
    "title": "Alias already exists",
    "status": 409,
    "detail": "A prompt with alias 'meta-description' already exists."
}
```

{% endcode %}

## Examples

{% code title="cURL" %}

```bash
curl -X POST "https://your-site.com/umbraco/ai/management/api/v1/prompts" \
  -H "Authorization: Bearer YOUR_ACCESS_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
    "alias": "meta-description",
    "name": "Generate Meta Description",
    "instructions": "Write a meta description..."
  }'
```

{% 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/add-ons/prompt/api/create.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.