# Judge AI output

This endpoint evaluates the performance of generative AI models by verifying multiple text outputs. It returns statistical analysis results, providing insights into the accuracy and reliability of the AI-generated content.

Endpoint: POST <https://api.deepverify.ai/v1/deepverify/judge-ai&#x20>;

**Request Example**&#x20;

```bash
curl -X POST "https://api.deepverify.ai/v1/deepverify/ai-output" \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
    "texts": [
        "AI-generated report for legal contracts.",
        "AI summary of patient records for healthcare claims.",
        "AI-generated ESG compliance report."
    ]
}'

```

**Response Example**&#x20;

```json5
{
  "total_texts": 3,
  "verified_texts": 2,
  "unverified_texts": 1,
  "accuracy_rate": 0.67,
  "details": [
    {
      "text": "AI-generated report for legal contracts.",
      "verified": true,
      "confidence_score": 0.85
    },
    {
      "text": "AI summary of patient records for healthcare claims.",
      "verified": false,
      "confidence_score": 0.45
    },
    {
      "text": "AI-generated ESG compliance report.",
      "verified": true,
      "confidence_score": 0.90
    }
  ]
}

```

**Parameters**&#x20;

* **texts** (array): A list of multiple AI-generated text outputs to be verified.&#x20;

**Response Fields**

* **total\_texts** (integer): The total number of text instances submitted.&#x20;
* **verified\_texts** (integer): The number of texts that were successfully verified.&#x20;
* **unverified\_texts** (integer): The number of texts that were found to contain disinformation or inaccuracies.&#x20;
* **accuracy\_rate** (float): The percentage of verified texts out of the total.&#x20;
* **details** (array): A breakdown of each text’s verification result, including the confidence score and verification status.

## Create a new user

<mark style="color:green;">`POST`</mark> `/users`

\<Description of the endpoint>

**Headers**

| Name          | Value              |
| ------------- | ------------------ |
| Content-Type  | `application/json` |
| Authorization | `Bearer <token>`   |

**Body**

| Name   | Type   | Description      |
| ------ | ------ | ---------------- |
| `name` | string | Name of the user |
| `age`  | number | Age of the user  |

**Response**

{% tabs %}
{% tab title="200" %}

```json
{
  "id": 1,
  "name": "John",
  "age": 30
}
```

{% endtab %}

{% tab title="400" %}

```json
{
  "error": "Invalid request"
}
```

{% endtab %}
{% endtabs %}


---

# 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://factagora.gitbook.io/deepverify/api-reference/judge-ai-output.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.