> For the complete documentation index, see [llms.txt](https://docs.aicrisk.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.aicrisk.com/admin/agent-scanner-defaults/topic-scanner.md).

# Topic Scanner

Scan for inappropriate and unwanted topics:

<figure><img src="https://2455207419-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FnZwCwAN15BUJcXMA5avi%2Fuploads%2FfFrUwCAz7KGqQVkFrqSz%2Fimage.png?alt=media&amp;token=c913eb8d-504f-4603-83d2-4c8fb692e152" alt=""><figcaption></figcaption></figure>

<figure><img src="https://2455207419-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FnZwCwAN15BUJcXMA5avi%2Fuploads%2FSQ1BNA1WF82qUo2tf9wz%2Fimage.png?alt=media&amp;token=97b583e9-fc69-45a1-936c-626e1d123e6d" alt=""><figcaption></figcaption></figure>

**Purpose:** The Topic Scanner is designed to analyze text inputs and identify the main topics or themes discussed within the content.

**Functionality:** It employs topic modeling techniques to extract key topics from text data based on the distribution of words and their relationships.

**Implementation:** The scanner processes text inputs using probabilistic algorithms to identify clusters of words that frequently co-occur and represent coherent topics. It may also incorporate natural language understanding (NLU) techniques to infer the meaning and context of the text.

**Usage:** The Topic Scanner is utilized to understand and categorize textual content automatically.