AI Agents

AI Agents can transform the ecommerce operations by enabling intelligent automation.

Emporix Agentic AI introduces AI-powered agents as a new way of working, transforming ecommerce operations by enabling intelligent automation. These agents are designed to take on business processes, simplify operations, and unlock greater efficiency for merchants.

Instead of relying on manual effort for repetitive or time-consuming tasks, involve these intelligent agents to react to events happening in the system and carry out some actions automatically. This approach not only saves time but also creates opportunities to scale business operations without adding complexity.

There are two primary types of agents within the Emporix Agentic AI:

Predefined agents

These are ready-to-use solutions provided by Emporix for common ecommerce needs. They are designed to run in the background, seamlessly integrating into business workflows. Emporix offers an Agents Library to make their adoption easier, which is an expandable catalogue of these prebuilt solutions.

Custom agents

For unique business requirements, merchants can use the Agentic AI to create and run custom agents. This offers full control over various aspects, allowing businesses to design agents tailored to their exact processes, compliance requirements, and customer expectations. You decide which language model (LLM) powers the agent, which tools are attached, and which MCP-based capabilities are available.

Custom AI Agents

Example use cases that the custom agents might come in handy:

• Connecting to OpenAI - Custom agents can be configured to use your own enterprise API token for GDPR-compliant production environments when connecting to market-leading Language Models like OpenAI. This allows for sophisticated AI interactions while maintaining compliance.

• Integrating with External Business Systems - Agents can be granted access to external MCP servers to securely interact with systems like ERP (Enterprise Resource Planning), CRM (Customer Relationship Management), or other specialized services. This enables agents to:

  • Fetch product availability directly from an ERP system.

  • Process purchase orders by communicating with your ERP system.

• Managing Credentials for Third-Party Services - Custom agents can manage credentials for various other third-party services or integrations, ensuring secure communication and automation across your entire digital landscape.

Custom agents don’t have to work in isolation. The platform allows you to create multiple agents and connect them, enabling them to operate as a team. This teamwork approach is especially powerful when solving complex business goals that require multiple steps or domain-specific expertise.

The example custom agents chain might look as follows:

1. One agent fetches product data from an ERP system.

2. A second agent analyzes that data for compliance or profitability.

3. A third agent updates the ecommerce catalog accordingly.

Working together, the agents form a coordinated workflow that is more effective than any single agent working on its own.

The Custom Agents feature makes Emporix not just a platform with AI capabilities, but a truly extensible agentic ecosystem. By combining predefined agents with custom-built ones, you as a merchant can automate, adapt, and innovate with precision — building agent teams that reflect the way your business really works.

Creating a custom agent

1

Choose to create an agent

In the Management Dashboard, go to the Agentic AI -> AI Agents. Choose Add new agent.

2

Provide configuration details

In the agent configuration form, provide the details to define the agent's identity, capabilities, and intelligence settings. Each field in the configuration is important to ensure that the agent behaves as expected and integrates seamlessly into your workflows.

Icon and Tags

For better searchability and visibility among other agents, you can change the agent's icon and add tags that fit to its functionality.

• ID - The unique identifier of the agent. This ID is critical, as it is used whenever the agent is triggered through an API endpoint.

• Agent Name - A human-readable name for the agent, used for identification in the dashboard.

• Description - A text field where you can describe the agent’s purpose and what tasks it is designed to handle.

• Required scopes - The access scopes necessary for a user to be able to trigger the agent. Select one or more from the list:

  • Anonymous - An anonymous user can invoke the agent.

  • Customer - A logged-in customer can invoke the agent.

  • Employee - A logged-in merchant employee can invoke the agent.

  • Integration - An external integration, like for example ERP or CRM system, can invoke the agent.

• Trigger Type - Define how the agent is activated:

  • API – Call the Emporix endpoints to trigger the agent. This is useful when you want to start an agent with specific content or data passed through an API invocation. You can also use this option to include the agent in an Digital Processes.

  • Commerce Event – Make the agent listen to specific commerce-related events happening in the system (for example, order-created) and act immediately when those events occur. Select the ones to act upon from the available commerce events list.

  • Slack - The option available only for the Support Agent type to call the agent from Slack tool.

• User Prompt - The core of your agent’s intelligence. Define how the agent should operate.

• Template Prompt - The generic prompt used for predefined agents, it describes general operation for agents of a specific type.

• MCP Servers - Extend the agent with MCP servers, granting access to additional tools and data sources. Two types are available:

  • Emporix MCP – Built-in MCP Servers provided by Emporix. Select which server and which tools are available to the agent.

  • Custom MCP – External servers you configure yourself (for example, ERP or CRM). Define custom MCP in the AI MCP view before you attach them to your agent.

• Native Tools - Extend the agent with native tool capabilities, such as Slack integration. For example, the agent can use the Slack tool to collaborate with humans in context-aware Slack channels. Prepare tools upfront in the AI Tools view.

• Agent Collaboration - Connect one or multiple agents together, allowing them to operate as a team. In the Description, define when the agent should hand over an action to another agent. You can attach as many agents as you need to create multi-step, collaborative workflows.

• LLM Configuration - Each agent can be powered by a different language model (LLM). This gives you the flexibility to choose the best option for your specific use case. Configuration options include the following:

  • Provider - Choose the provider that powers the agent:

    • Emporix OpenAI Token – For testing purposes only. This option lets you get started quickly without creating an external account. However, this token must not be used for production. For production, to make the solution GDPR compliant, use your own enterprise license or custom model. Notice there is a limited number of tokens available per tenant:

      • input tokens: 2 000 000

      • output tokens: 500 000

    • OpenAI

    • Google

    • Anthropic

    • Self-hosted model served through the Ollama interface

  • Model - Each LLM provider offers multiple models (for instance, OpenAI GPT-4, Claude Sonnet 4.5, Gemini 2.5 Flash, and more). Specify the model for your agent.

  • Temperature - Define the level of randomness and creativity of your agent. Values range from 0.0 to 1.0.

    • Lower values (for example, 0.1) → More predictable, rule-following outputs.

    • Higher values (for example, 0.8) → More creative, useful for tasks like product description generation.

  • Max Tokens - Set the maximum length of responses the agent can generate, based on the particular model's specification and your use case.

  • Token - Select a previously configured token (from the AI Tokens view) to be used for communication with the LLM provider.

  • Recursion Limit - Define how many iterations the agent is allowed to perform before it stops the execution. This parameter prevents infinite loops and ensures safety and stability of the agent.

  • Enable Memory - Toggle the memory option on if you want the agent to keep the conversational data within the session. For example, it is useful for chatbots that need to remember previous queries and answers to be able to make logical references and adequate data matching. The memory is kept within one session-id.

Prompt

A well-written and designed prompt guides the agent’s reasoning, behavior, and tone. We recommend learning about prompt engineering best practices to ensure your agent performs consistently and effectively.

3

Save the agent

Once ready, confirm your agent definition with Save.

As a result, the agent is available on the My Agents list.

Emporix provides ready-to-use predefined agents. Check out the AI Agents Library to learn when to use them and how to enable them in your Emporix instance.