> 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/learning-trails/learning-trails.md).

# Agentic Commerce Intelligence Learning Trails

Explore Agentic Commerce Intelligence through independent trails for library agents and custom agents, each as a way to get familiar with agentic possibilities.

Each trail gathers the how-tos for one outcome. They sit alongside the detailed reference guides and walk through examples to help you get started.

{% hint style="info" %}
These trails focus on Agentic AI inside the tenant. Partners and implementers who need IDE tooling can start with [Agentic Engineering](/agentic-commerce-intelligence/agentic-engineering/agentic-engineering.md#get-started) instead.
{% endhint %}

## Agents

An **agent** is a configured automation in the tenant, not a general chat assistant. You define the following elements:

* A **model** (LLM) and **prompt** that shape how the agent reasons
* A **trigger** that starts a run – for example, an API call, or Slack or Microsoft Teams when communication tools are set up
* Optional **tools** that let the agent read or change tenant data – for example, built-in commerce MCP tools, RAG, communication, or custom MCP

You check completed runs in **AI Logs**.

## Library agents and custom agents

In Agentic AI you can use either of the following:

* **Library agents** – ready-made templates you enable and activate when a template matches your use case
* **Custom agents** – agents you assemble yourself when no template fits

## Access preparations

Before you start a trail, make sure you have the following access:

* Emporix tenant access – sign-in access to the tenant used for the trail
* Management Dashboard access – access to **Agentic AI**
* Emporix API credentials – a Client ID and Secret that can request a service access token with `ai.agentexecution_manage`, which the agent chat endpoint requires

{% hint style="info" %}
An agent can also restrict who may call it with **Required scopes**. For details, see [Define activation rules](/agentic-commerce-intelligence/agentic-intelligence/agents.md#define-activation-rules).
{% endhint %}

## Choose a trail

Choose a trail based on whether you want a library template or a custom agent.

<table data-card-size="large" data-view="cards"><thead><tr><th align="center"></th><th align="center"></th><th align="center"></th><th data-hidden data-card-target data-type="content-ref"></th></tr></thead><tbody><tr><td align="center"><i class="fa-language">:language:</i></td><td align="center"><strong>Enable a library agent</strong></td><td align="center">Start from a ready-made template when one matches your use case.</td><td><a href="/agentic-commerce-intelligence/learning-trails/learning-trails/enabling-your-first-library-agent.md">Enabling Your First Library Agent</a></td></tr><tr><td align="center"><i class="fa-robot-astromech">:robot-astromech:</i></td><td align="center"><strong>Create a custom agent</strong></td><td align="center">Assemble your own agent when no library template fits the process.</td><td><a href="/agentic-commerce-intelligence/learning-trails/learning-trails/creating-your-first-custom-agent.md">Creating Your First Custom Agent</a></td></tr></tbody></table>

{% hint style="success" %}
When you finish a trail, use the other Agentic Commerce Intelligence guides for options these paths do not cover, such as [AI Agent Library](/agentic-commerce-intelligence/agentic-intelligence/agent-library.md), [AI Agents Configuration](/agentic-commerce-intelligence/agentic-intelligence/configuration.md), [AI Logs](/agentic-commerce-intelligence/agentic-intelligence/logs.md), and [AI Best Practices](/agentic-commerce-intelligence/agentic-intelligence/best-practices.md).
{% 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 by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://developer.emporix.io/agentic-commerce-intelligence/learning-trails/learning-trails.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

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.
