# Image Reader

Majoriy of Curve's Premium Automod is fitted with an image reader. Capable of detecting words such as [Advertisement](https://guide.curvebot.xyz/auto-moderation/advertising-detection), [Profanity](https://guide.curvebot.xyz/auto-moderation/toxicity-prevention), [Explicit Messages](https://guide.curvebot.xyz/auto-moderation/premium-automations/explicit-messages) and more.

## Settings

As we use computer vision to moderate, Curve will highlight moderated text for any automod violation in a <mark style="color:red;">**red text**</mark> ansi format if it is supported.

### Examples

Here we will provide you with showcase concepts ONLY of what you can imagine the reader works.&#x20;

<figure><img src="/files/hsW6Fek5CQ0oB7aWlmwH" alt="Curve Automod Logging Example Image Highlighted in a Red Text alongside the image sent by the user" width="375"><figcaption><p><strong>EXAMPLE SHOWCASE</strong></p></figcaption></figure>


---

# 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://guide.curvebot.xyz/auto-moderation/premium-automations/image-reader.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.