> For the complete documentation index, see [llms.txt](https://developer.emporix.io/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://developer.emporix.io/frontend/customer-account/emporix-ai-agent.md).

# Emporix Frontend Agent

The Emporix Frontend Agent is your personal assistant inside the Emporix platform, always ready to help you manage your commerce activities. It's designed to automate routine tasks, guide you through complex workflows, and make your day-to-day business smoother. The AI embeded in the frontend understands your commerce context and can access everything within your account, from profile details and order history to quotes, returns, and invoices - allowing it to support you through the entire customer journey.

<figure><img src="/files/yrdUoOkr1Y3REhxaFnNa" alt=""><figcaption><p>Emporix Frontend Agent interface</p></figcaption></figure>

## Usage examples - what can the Frontend Agent do?

### Helping out to find your way

Need to find a past order or check a quote? Just ask:

> “Show me my latest orders.” “What’s the status of my open quotes?”

The agent instantly retrieves that information and guides you to the right section in your dashboard.

It can also help you review your profile, update details, or show you what’s new in your account — saving you clicks and time.

### Product recommendations

The Frontend Agent is not only reactive, it's proactive too. Based on your past purchases, preferences, or browsing history, it can suggest products you might be interested in.

If you like the agent's recommendation, it will ask:

> "Do you want to add this product to the cart?"

When the Frontend Agent confirms the choice with you, it gives you a quick recap of your cart, and asks if you'd like to proceed to checkout.

### Cart reviews and orders optimization

Before you confirm your purchase, the Frontend Agent can analyze your cart, it can check the product availability, delivery timelines, and fulfillment options. If the agent sees something that can't be delivered on time, it can automatically suggest substitute products that ship faster, recommend alternative suppliers, or adjust your order for quicker delivery.

This helps in reducing delays, avoiding stock issues, and ultimately minimizing order cancellations or abandoned carts.

### Returns automation

If you encounter a damaged product or any issue, you can tell the agent directly:

> "I received a damaged item, please create a return for the order number #EON123."

The agent then automatically creates a return and triggers the appropriate workflow using integrated systems.

The Frontend Agent also operates under a *human-in-the-loop* model: it can either fully automate allowed actions, like ticket creation or data lookup, or, for restricted processes, it involves a support specialist to review and complete the case.

Once resolved, the ticket status is automatically updated in your frontend account, keeping you informed every step of the way.

{% hint style="info" %}
To learn more about the Frontend AI Agent and its capabilities, see the [Frontend Agent](/agentic-commerce-intelligence/agentic-intelligence/agent-library/frontend-agent.md) documentation.
{% endhint %}


---

# 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:

```
GET https://developer.emporix.io/frontend/customer-account/emporix-ai-agent.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.