# Raven Community AI Agents

Raven now supports a new type of AI Agent called **Community AI Agents**, designed to manage and automate actions for public interactions such as comments on social media posts.

Community AI Agents complement the existing **DM AI Agents**, which focus on direct messages.

***

### **What Community AI Agents Do**

Community AI Agents can:

* Reply to comments on posts
* Perform moderation actions (hide or delete comments)
* Send private replies
* Assign or close support tickets

**Currently supported:**

* Facebook comments
* Instagram comments

**Coming soon:**

* YouTube comments
* App Store reviews
* Play Store reviews

***

### **How to Create a Community AI Agent**

1. Navigate to **Raven**
2. Click **+ Create AI Agent**
3. Choose **Community Agent** in the modal
4. Provide an **agent name** and a brief **description**
5. Click **Save & Continue**
   * Use **Save as draft** if you want to complete it later

***

### **Training Your Community AI Agent**

Under **Resources**, you can provide the data your agent will use to generate accurate responses:

#### **1. URLs**

* Crawl website links and extract content to train the agent.

#### **2. Docs**

* Upload files or documents that contain relevant product or business information.

#### **3. Q\&A**

* Add FAQs or your own question–answer scenarios to guide the agent’s response patterns.

***

### **Configuring Actions**

Click **+ Add Actions** to open the actions sidebar. The following actions are available for Community Agents:

#### **General Actions**

1. **API Call** — connect to external systems or webhooks
2. **Hide** — hide a comment from public visibility
3. **Delete** — permanently delete a comment

#### **Support Actions**

1. **Send Private Reply** — send a direct message to the commenter
2. **Assign Ticket** — assign the ticket to a human agent or another AI Agent
3. **Close Ticket** — mark the ticket as resolved

***

### **Testing Your Agent**

In the **Test** section, you can interact with your Community AI Agent in a sandbox environment.\
Use this to validate tone, accuracy, and expected behavior before deploying.

***

### **Deploying Your Community AI Agent**

Once you’re satisfied with your agent’s performance:

1. Go to the **Deploy** section
2. Follow the steps to deploy the agent on supported channels
3. Once deployed, the agent will begin responding to comments based on your configuration

***

Raven Community AI Agents help you automate engagement, improve moderation, and deliver quick, intelligent responses across your social platforms.

If you need further assistance, our support team is always available.


---

# 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://docs.myalice.ai/release-log/raven-community-ai-agents.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.