> For the complete documentation index, see [llms.txt](https://docs.onlymonster.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.onlymonster.ai/team-and-security-management/context-detection.md).

# Context Detection

Context Detection is a next-generation AI protection layer that analyzes the meaning and intent behind outgoing messages — not just individual keywords. Unlike traditional filters that rely on exact word matches, Context Detection evaluates the full context of phrases to identify violations that might otherwise go unnoticed.

Context Detection works on three platforms: **OnlyFans**, **Fansly**, and **Telegram**.

### **How It Works**

Context Detection functions as a global filter, operating independently from other Message Guard layers, including:

* **Red/Yellow word lists,**
* **Custom lists,**
* **Bypass Protection.**

The system uses a proprietary detection algorithm that:

1. Identifies messages containing trigger words from an internal monitoring list
2. Analyzes the full context and intent of the message
3. Flags violations based on meaning, even when no explicitly prohibited words are used

Example Detection:

* Message: "Maybe we could chat somewhere else?"
* Result: Flagged as a Direct Contact violation even though it contains no explicitly banned terms.

This layer is particularly effective at detecting indirect or conversational phrasing used to bypass keyword-based filters.

### **Protected Topics**

**Context Detection monitors the following four violation categories:**

* **Direct Contact** - Attempts to move the conversation to external messaging platforms
* **Real-world Meetup Escort** - Proposals for physical meetings or encounters
* **Third-party Payment** - Attempts to redirect payments outside the platform
* **Underage** - Content or language related to minors.

<figure><img src="https://3576754298-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FJ3tUjWV0i06zjZEIvwPN%2Fuploads%2FfoPHGrAT8GTqewdep4FU%2F%D0%BA%D0%BF%D0%BA%D1%86%D0%BA%D1%83%D0%BF.png?alt=media&amp;token=e6fae997-d419-4a55-891d-1c573ee3f483" alt=""><figcaption></figcaption></figure>

Important Notes:

* Context Detection works in addition to your existing word filters, providing an extra layer of protection
* Context Detection applies to all platforms and cannot be turned off for an individual platform
* All violations are logged in the standard Message Guard Logs, with the topic clearly identified.

**Relationship to Other Protection Layers**

Context Detection is designed to work alongside your existing Message Guard configuration:

* **Independent Operation** - It functions separately from Red/Yellow/Custom word lists.
* **Dual Protection -** A message can be blocked by keyword filters, Context Detection or both.
* **Unified Logging -** All violations—regardless of detection method—appear together in the Message Guard Logs, clearly labeled with the appropriate detection source.

**Summary**

Context Detection adds an intelligent, meaning-based protection layer that adapts to real conversation patterns.\
You keep full control of your traditional word lists, while Context Detection enhances security by identifying violations based on intent, not just keywords.

If you have any suggestions or requests regarding the detected topics, contact our support team.\ <br>


---

# 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.onlymonster.ai/team-and-security-management/context-detection.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.
