AI Agent Library

Make use of the predefined agents available out-of-the-box.

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	Template that creates Complaint Categorization, Complaint Audit and Complaint Agent instances. Streamlines customer complaint handling and automates aspects of customer service.
Transactions security	Anti-Fraud Agent	Template that creates Anti-Fraud Scoring, Anti-Fraud Audit, and Anti-Fraud Agent instances. Detects and responds to suspicious activity before it escalates.
Communication and support	Support Agent	Template that creates a Support Agent instance. Connects Emporix to Slack or MS Teams so teams can query orders, returns, and product updates directly in their workspace.
Translations	Translation Agent	Translates database content into multiple languages to speed up product publication.
Storefront guidance and search	Frontend Agent	Guides customers on the storefront, performs actions on their behalf using contextual data, and supports natural-language product and order search with RAG AI tools.
Operations optimization	Agentic Filters Creator Assistant	Helps define constraints and rules for triggering custom agents.
Structured agent output	Agentic JSON Schema Assistant	Generates JSON Schema for the Output Format field when configuring custom agents.
Log investigation	Agentic Log Analysis Assistant	Analyzes request logs to detect runtime failures, identify root causes, and answer follow-up questions. Enable it from Predefined Agents, or when you first select Analyze Logs.
Cloud Function generation	Cloud Function Assistant	Generates and edits deployable HTTP Cloud Functions from a natural-language request in Hosting. Enable it from Predefined Agents, or when you first select AI Cloud Function.
Dynamic MCP tool setup	Agentic Dynamic MCP Tool Assistant	Infers MCP tool fields from Cloud Function source when you configure a dynamic MCP server. Enable it from Predefined Agents, or when you first select a Cloud Function on a dynamic MCP.

Support, Complaint, and Anti-Fraud templates create generic agent instances. Complaint and Anti-Fraud templates expand into multiple collaborating instances; the Support template creates a single Support Agent that owns Slack or MS Teams channel setup when human collaboration is required.

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.

1

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

2

Add name and description

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

Agent creation form

3

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

4

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.

For more information about the meaning of different agent settings, see the AI Agents.

5

Activate agent

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

Agent enabled

The agent is ready to take action when needed.