# Xurrent AI Agent

The **Xurrent AI Agent** is a an AI Agent that integrates Autom Mate with Xurrent service management.

It uses an AI model (OpenAI or Azure OpenAI) for intent understanding and Autom Mate for controlled execution of Xurrent operations through APIs.

***

### Overview

The agent provides the following capabilities:

* Retrieve and view requests
* View resolved requests
* Add notes to requests
* Search knowledge base articles
* Create requests

All interactions are executed through Autom Mate while **Xurrent remains the system of record**.

***

### Prerequisites

#### Autom Mate

* Access to **AI Agent Composer**\
  👉 [AI Agent Composer](https://docs.autommate.com/userguide/ai-agent-composer)

***

#### AI Model

The agent requires one of the following providers:

* **OpenAI**
* **Azure OpenAI**

Credentials must be configured in Autom Mate Vault:

👉 [Vault](https://docs.autommate.com/userguide/product-features/management/vault)

Credential configuration includes:

* API Key
* Endpoint (for Azure OpenAI)
* Model / Deployment selection

***

#### Xurrent

You must provide:

* **Xurrent API access**
* **Authentication**

Supported methods:

* API Key
* OAuth

Credentials must be configured in Autom Mate Vault.

***

### Required Permissions

The configured Xurrent user must have access to:

| Resource  | Permissions          |
| --------- | -------------------- |
| requests  | Create, Read, Update |
| knowledge | Read                 |

All API operations are executed using these permissions.

***

### Knowledge Integration

Xurrent can be used as a knowledge source through Autom Mate.

* Connected via **Knowledge → Applications → Xurrent**
* Enables retrieval from:
  * Knowledge articles
  * Service-related data

This allows the agent to perform RAG-based responses using Xurrent content.

***

### Capabilities (Out-of-the-Box)

The agent includes predefined Xurrent actions:

#### Request Management

* Get request
* Get resolved requests
* Add note to request
* Create request

***

#### Knowledge Access

* Search knowledge articles

***

### Execution Flow

1. User sends a request via a channel
2. AI model (OpenAI / Azure OpenAI) interprets intent
3. Autom Mate maps the intent to a predefined action
4. Xurrent APIs are invoked
5. Response is returned

***

### Execution Model

* **AI Layer** → intent detection and response generation
* **Autom Mate Layer** → skill execution and orchestration
* **Xurrent Layer** → system of record

***

### Safety and Permissions

By default:

* Read operations are enabled
* Write operations include:
  * Create request
  * Add note to request

All actions are:

* Executed using configured credentials
* Restricted by Xurrent permissions
* Controlled through Autom Mate

***

### Extending the Agent

Additional functionality can be introduced by:

* Using available skills in Autom Mate
* Creating custom actions and workflows

👉 [AI Agent Composer](https://docs.autommate.com/userguide/ai-agent-composer)

***

### Channels

The Xurrent AI Agent supports:

* WhatsApp
* Microsoft Teams
* Mate Chat

***

### Summary

The Xurrent AI Agent provides:

* AI-driven interaction with Xurrent
* Predefined request and knowledge operations
* Secure API-based execution
* Extendable skill-based architecture
