> 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/ai-magic-assistant/ai-suggestions.md).

# AI Suggestions

AI Suggestions generates ready-to-send replies inside a chat. A member opens a chat, clicks a reply button in the message bar, and receives a suggestion written for the last fan message.

Every reply runs either on the built-in OnlyMonster engine or on your own model through an AI Gateway preset.

#### Where to Find It

Open **AI Tools → AI Suggestions** — the same sidebar section as **AI Gateway** and **Translate**.

*AI Suggestions is available for OnlyFans accounts only.* 

The module has three tabs:

| Tab           | What it holds                                                                    |
| ------------- | -------------------------------------------------------------------------------- |
| **Accounts**  | Which replies are running on each account, and how they behave in chat           |
| **Replies**   | Every reply in the organization: built-in system replies and the ones you create |
| **Analytics** | Usage statistics for suggestions                                                 |

#### System and Custom Replies

| Type       | Badge             | What it is                                                             | What you can configure                              |
| ---------- | ----------------- | ---------------------------------------------------------------------- | --------------------------------------------------- |
| **System** | blue **System**   | Built-in replies. They run on the OnlyMonster engine                   | Writing style only — the prompt and model are fixed |
| **Custom** | yellow **Custom** | Replies created by your organization. They run on an AI Gateway preset | Name, preset, prompt and post-processing            |

Ten system replies are available out of the box:

| Reply           | What it does              |
| --------------- | ------------------------- |
| **Engage**      | Draws fan into chat       |
| **Bump**        | Brings quiet chat back    |
| **Innocent**    | Keeps tone sweet and shy  |
| **Bullet**      | Opens with quick flirt    |
| **Quick Reply** | Keeps chat moving fast    |
| **Spicy**       | Turns up the flirt        |
| **PPV**         | Turns chat into sale      |
| **Playful**     | Teases to keep it fun     |
| **Question**    | Sparks curiosity to reply |
| **Upsell**      | Leads fan toward sale     |

#### How It Works

Using the built-in replies requires nothing beyond connecting them to accounts. Running suggestions on your own model takes four steps:

1. **AI Tools → AI Gateway** — add an API key.
2. **AI Tools → AI Gateway** — create a preset: select a model and set its parameters.
3. **AI Tools → AI Suggestions → Replies** — create a custom reply and select the preset.
4. **AI Tools → AI Suggestions → Accounts** — connect the reply to your accounts.

Steps 1 and 2 are covered in AI Gateway. For steps 3 and 4, see Custom Replies and Connecting Replies to Accounts.

Presets are shared across the whole organization: the same preset can power a custom translator and a custom reply at the same time. 

#### How Suggestions Appear in Chat

The replies enabled on the account are displayed as buttons in the message bar of the chat. A member clicks a button, the suggestion is generated from the recent conversation and the last fan message, and the text is placed in the input field — nothing is sent to the fan automatically.

The order of the buttons is set on the account, and **Auto-Generate** can produce one suggestion the moment a chat opens. Both are configured in the account settings — see Connecting Replies to Accounts.


---

# 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 dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://docs.onlymonster.ai/ai-magic-assistant/ai-suggestions.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

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.