# AI Agent Library

To make adoption easier, Emporix provides the Agents Library with prebuilt, ready-to-use solutions for common ecommerce needs. Among them are the Complaint Agent, designed to streamline how customer complaints are handled, the Anti-Fraud Agent, built to detect and respond to suspicious activity before it becomes a problem, the Support Agent, responsible for smooth communication about any issue, and the Translation Agent that increases productivity. These agents run in the background, seamlessly integrating into business workflows, and help merchants ensure a more efficient, secure, and customer-friendly operation.

<figure><img src="https://1530167654-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F8GgoeZEZYjZrpjOU6w52%2Fuploads%2Fgit-blob-e0ea117995b78ddacea8a268d654786e36268fcb%2Fagent_library.png?alt=media" alt="AI Agent library"><figcaption><p>AI Agent Library</p></figcaption></figure>

## Predefined agents

Here are some use cases you can cover with the predefined agents from Emporix library:

* Complaints management - Use the Complaint Agent designed to streamline how customer complaints are handled, automating aspects of customer service.
* Transactions security - Use the Anti-Fraud Agent that detects and responds to suspicious activity before it escalates into a problem, enhancing security for transactions.
* Communication and support - Use the Support Agent that enables the Slack tool. The agent bot is installed in your Slack workspace to allow teams to interact with the Emporix system directly within Slack channels. For example, you can inquire about orders, returns, or product updates right where your team communicates, fostering seamless collaboration.
* Translations - Use the Translation Agent that you can configure to provide translations of the data from your database to different languages, saving time when preparing the products for publication.
* Storefront guidance and search - Leverage the Frontend Agent that can guide your customers throughout the overall shopping experience directly from the storefront. The Agent takes care of performing certain actions on behalf of a customer due to its access to contextual data. Additionally, when connected to RAG AI tools, the Agent provides semantic search functionality, enabling natural language product queries.

## Enabling a predefined agent from the library

To enable an agent based on the predefined agent, create a new instance out of the selected template.

{% stepper %}
{% step %}
**Browse the predefined agents library**

In the Management Dashboard, go to the **Agentic AI** -> **AI Agents**. In the **Predefined Agents** section, you can see all the agents available out-of-the-box for your use. Select the agent template and choose **Add agent**.

<figure><img src="https://1530167654-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F8GgoeZEZYjZrpjOU6w52%2Fuploads%2Fgit-blob-72847067d5895f03b745313c3ec9f95507cf0edb%2Fagentic_add_agent.png?alt=media" alt="Add agent"><figcaption><p>Add AI Agent</p></figcaption></figure>
{% endstep %}

{% step %}
**Add name and description**

Customize the agent name and description to better suit your task.

<figure><img src="https://1530167654-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F8GgoeZEZYjZrpjOU6w52%2Fuploads%2Fgit-blob-5b1c32fa511552cd6af724e71f4d686cb62c3732%2Fagentic_agent_form.png?alt=media" alt="Agent creation form" width="375"><figcaption><p>Agent creation form</p></figcaption></figure>
{% endstep %}

{% step %}
**Save the agent**

Confirm creation with **Save**. The agent is created by the system and you get a notification that the agent is available in the **My agents** section.

<figure><img src="https://1530167654-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F8GgoeZEZYjZrpjOU6w52%2Fuploads%2Fgit-blob-6f31fa7bc6ba9a7fa6b79f3e87f5b27cfc86f36b%2Fagentic_agent_created.png?alt=media" alt="Agent created" width="375"><figcaption><p>Agent created</p></figcaption></figure>
{% endstep %}

{% step %}
**Configure the agent**

To adjust the way the agent operates, find the agent on the **My agents** list and choose the **Configure** option.

<figure><img src="https://1530167654-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F8GgoeZEZYjZrpjOU6w52%2Fuploads%2Fgit-blob-1ffb54ba6931753b7a9d6571717fcccd7ca890e3%2Fagentic_configure.png?alt=media" alt="Configure agent" width="250"><figcaption><p>Configure agent</p></figcaption></figure>

In agent edition mode, verify the default setup and modify the agent prompt, tools, collaboration, LLM, or other settings so that the agent fits your use cases. When done, save the changes.

{% hint style="success" %}
For more information about the meaning of different agent settings, see the [AI Agents](https://developer.emporix.io/agentic-commerce-intelligence/agents#creating-a-custom-agent).
{% endhint %}
{% endstep %}

{% step %}
**Activate agent**

From the **My agents** list, toggle active to enable the agent to work and react according to its purpose.

<figure><img src="https://1530167654-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F8GgoeZEZYjZrpjOU6w52%2Fuploads%2Fgit-blob-ffc561fbb66f45c9e2a4ec16e494cac7b6dafe6e%2Fagentic_agent_enable.png?alt=media" alt="Agent enabled" width="250"><figcaption><p>Agent enabled</p></figcaption></figure>
{% endstep %}
{% endstepper %}

The agent is ready to take action when needed.
