# Overview

{% embed url="<https://youtu.be/l89A5rGmfGQ>" %}

{% content-ref url="build" %}
[build](https://docs.usepylon.com/pylon-docs/ai-agents/build)
{% endcontent-ref %}

{% content-ref url="test" %}
[test](https://docs.usepylon.com/pylon-docs/ai-agents/test)
{% endcontent-ref %}

{% content-ref url="deploy" %}
[deploy](https://docs.usepylon.com/pylon-docs/ai-agents/deploy)
{% endcontent-ref %}

{% content-ref url="monitor-and-iterate" %}
[monitor-and-iterate](https://docs.usepylon.com/pylon-docs/ai-agents/monitor-and-iterate)
{% endcontent-ref %}

## How to think about AI Agents <a href="#expectation-setting" id="expectation-setting"></a>

You can think about AI Agents as an extension of your team, users who can be assigned to issues. They can be used for many things, including:

* Handling of questions based on knowledge base or documentation content
* Initial information collection from customer
* Gathering of context internally for your team
* End-to-end resolution of issue

You can use AI Agents to attempt to automate the pieces of your workflow you want to - **expect it to be an iterative process** to identify the best workflows to automate, and to build your skills in instructing the agent.