> 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/agentic-commerce-intelligence/agentic-intelligence/agent-library.md).
# 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.
AI Agent Library
## Predefined agents
Here are some use cases you can cover with the predefined agents from Emporix library:
| Use case | Agent | Description |
| ------------------------------ | ----------------------------------------------------------------------------------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------- |
| Complaints management | [Complaint Agent](/agentic-commerce-intelligence/agentic-intelligence/agent-library/complaint-agent.md) | Streamlines customer complaint handling and automates aspects of customer service. |
| Transactions security | [Anti-Fraud Agent](/agentic-commerce-intelligence/agentic-intelligence/agent-library/anti-fraud-agent.md) | Detects and responds to suspicious activity before it escalates, enhancing transaction security. |
| Communication and support | [Support Agent](/agentic-commerce-intelligence/agentic-intelligence/agent-library/support-agent.md) | Connects Emporix to Slack so teams can query orders, returns, and product updates directly in their workspace. |
| Translations | [Translation Agent](/agentic-commerce-intelligence/agentic-intelligence/agent-library/translation-agent.md) | Translates database content into multiple languages to speed up product publication. |
| Storefront guidance and search | [Frontend Agent](/agentic-commerce-intelligence/agentic-intelligence/agent-library/frontend-agent.md) | Guides customers on the storefront, performs actions on their behalf using contextual data, and supports natural language product search with RAG AI tools. |
| Operations optimization | [Agentic Filters Creator Assistant](/agentic-commerce-intelligence/agentic-intelligence/agent-library/filters-agent.md) | Helps define constraints and rules for triggering custom agents. |
| Structured agent output | [Agentic JSON Schema Assistant](/agentic-commerce-intelligence/agentic-intelligence/agent-library/json-schema-agent.md) | Generates JSON Schema for the **Output Format** field when configuring custom agents. |
## 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**.
Add AI Agent from the Library
{% endstep %}
{% step %}
**Add name and description**
Customize the agent name and description to better suit your task.
Agent creation form
{% 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.
Agent created
{% 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.
Configure agent
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](/agentic-commerce-intelligence/agentic-intelligence/agents.md#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.
Agent enabled
{% endstep %}
{% endstepper %}
The agent is ready to take action when needed.
---
# 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://developer.emporix.io/agentic-commerce-intelligence/agentic-intelligence/agent-library.md?ask=&goal=
```
`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.