> 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/certifications/cross-role-certification/agentic-commerce-intelligence-certification.md).
# Agentic Commerce Intelligence Certification
## **Who is it for?**
Solution consultants, technical consultants, and implementation partners who advise on or configure Agentic Commerce Intelligence (ACI) capabilities.
## **Description**
The Agentic Commerce Intelligence Certification is designed for professionals who work at the intersection of consulting and implementation for Emporix AI agents. It focuses on when to use ACI, how predefined agents map to business use cases, how to configure and activate agents, and the technical building blocks that connect agents to commerce data and workflows.
Participants demonstrate practical knowledge of the Agents Library, agent configuration (prompts, tools, tokens, and triggers), Emporix MCP integrations, and core agentic chat and runtime behavior.
**After completing this certification, you show that you are able to:**
* Explain the role of Agentic Commerce Intelligence in the Emporix platform
* Recommend the right predefined agent for common ecommerce scenarios
* Describe how to configure, activate, and operate custom and library agents
* Explain MCP domains, tokens, and Frontend MCP customer-context constraints
* Apply core agentic chat concepts such as session handling and asynchronous jobs
* Connect ACI capabilities to consulting and implementation conversations
## How to prepare
Focus on **Agentic Commerce Intelligence** from both a solution and configuration perspective.
{% hint style="info" %}
Stay practical. Combine use-case judgment with enough configuration and API knowledge to advise and implement confidently.
{% endhint %}
{% stepper %}
{% step %}
### Start with ACI fundamentals
Use the [Agentic Commerce Intelligence](https://developer.emporix.io/agentic-commerce-intelligence) documentation to understand:
* What ACI is and how it fits the Emporix architecture
* The difference between Agentic AI, the Agents Library, and AI Features
* How AI Smart Config and AI Smart Import support tenant setup and getting started
{% endstep %}
{% step %}
### Go deeper into agents and configuration
Focus on the areas covered by the exam:
* [AI Agents Library](https://developer.emporix.io/agentic-commerce-intelligence/agentic-intelligence/agent-library) use cases and when to enable each agent
* [AI Agents](https://developer.emporix.io/agentic-commerce-intelligence/agentic-intelligence/agents) configuration: prompts, models, scopes, triggers, and tools
* [AI Agents Configuration](https://developer.emporix.io/agentic-commerce-intelligence/agentic-intelligence/configuration) for tokens, tools (including RAG), and custom MCP
* [RAG AI Tool](https://developer.emporix.io/agentic-commerce-intelligence/agentic-intelligence/configuration/tools/rag) setup, indexing, and retrieval behavior
* [AI Agent Import/Export](https://developer.emporix.io/agentic-commerce-intelligence/agentic-intelligence/agent-import-export) for promoting agents across environments
* Agent monitoring with [AI Logs](https://developer.emporix.io/agentic-commerce-intelligence/agentic-intelligence/logs)
* [Agent API](https://developer.emporix.io/api-references/api-guides/artificial-intelligence/ai-service/api-reference/agent) for managing agent instances
* [Agent Chat API](https://developer.emporix.io/api-references/api-guides/artificial-intelligence/ai-service/api-reference/agent-chat) for starting agent conversations
* [Agent Logs API](https://developer.emporix.io/api-references/api-guides/artificial-intelligence/ai-service/api-reference/agent-logs) for searching and reviewing agent sessions
{% endstep %}
{% step %}
### Build your implementation perspective
Make sure you are comfortable with:
* [Emporix MCP Server](https://developer.emporix.io/agentic-commerce-intelligence/mcp-in-emporix/mcp) domains, Streamable HTTP transport, and MCP tokens
* Frontend Agent and Frontend MCP customer-context behavior
* Agentic chat flows, including `session-id` and asynchronous job polling
* Explaining ACI recommendations to both business and technical stakeholders
{% endstep %}
{% endstepper %}
Example: short ACI solution story
**Customer scenario:**\
A B2B merchant wants storefront assistants for logged-in buyers, Slack-based operations support, and automated complaint handling, without rebuilding every workflow from scratch.
**Solution story:**\
Start with the business outcomes: faster support, fewer manual lookups, and safer customer-scoped storefront actions. Then map those outcomes to ACI: enable relevant Agents Library templates, configure tools and triggers, and use MCP to connect agents to live commerce data.
**What you should be able to explain:**
* Which predefined agents fit the use cases
* What must be configured before agents can run reliably
* Where MCP and customer scope matter for storefront actions
* How teams monitor agent sessions and iterate on prompts or tools
{% hint style="success" %}
You are ready when you can recommend ACI solutions and explain how to configure and operate them with confidence.
{% 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, and the optional `goal` query parameter:
```
GET https://developer.emporix.io/certifications/cross-role-certification/agentic-commerce-intelligence-certification.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.