# Like a Design

Add a design to your personas liked collection. Save a design to your liked collection by creating a training.

### Endpoint

```
POST /v2/personas/:persona_id/trainings
```

### Parameters

| Parameter | Type   | Description                                                                                                                                                                              |
| --------- | ------ | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| image     | string | **Required.** Image URL of the design you want to like. You can upload it to Luw\.ai servers with [**/upload**](/api/luw.ai-api-documentation/introduction/uploading-files.md) endpoint. |
| extras    | string | *Optional.* Prompt of the liked design.                                                                                                                                                  |

### Example Request

```bash
curl -X POST https://api.luw.ai/v2/personas/123/trainings \
    -H "Authorization: Bearer YOUR_API_TOKEN" \
    -d "image=https://example.com/interior-design.jpg" \
    -d "extras=cozy living room"
```

### Response

```json
{
    "status": true,
    "training_id": 789
}
```

> **Note:** Using the training endpoint without a slot allows you to save **(like)** designs to your persona's collection.

To remove likes, you can use [**Remove Training Endpoint**](/api/luw.ai-api-documentation/personas/training-endpoints.md#delete-training) with **`training_id`** returns from Luw\.ai API.


---

# 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://luw-ai.gitbook.io/api/luw.ai-api-documentation/personas/like-a-design.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.