---
title: "How can I train using a Sitemap?"
description: "Learn how to use sitemaps when you train an agent."
url: https://help.agent.so/en/articles/65-how-can-i-train-using-a-sitemap
collection: "Training"
updated: 2024-04-12
language: en
---

# How can I train using a Sitemap?

Learn how to use sitemaps when you train an agent.

## What is a Sitemap?

An **XML sitemap** is **a list of the pages** on a website. It provides important information about the URLs on your website including pages, videos, images, files and what’s their relation.

## How to Train Your Agent with a Sitemap

To begin with, you need to have **a URL for the sitemap** you wish to use for training. Here's a step-by-step guide:

1.  **Find your sitemap**: This is usually located at [yourdomain.com/sitemap.xml](http://yourdomain.com/sitemap.xml). But remember, not all websites have a sitemap.xml. You'll have to ensure your website does, and you know its exact URL.
    
2.  **Enter the sitemap's URL**: Go to the training section in [Agent.so](http://Agent.so) and enter your sitemap's URL. This is how you tell the system to train your agent with data from your site.
    

![](https://staticfiles.gleap.io/ghelparticle/Nehz0EInyZ3klXHSHLirFZnkiGcxw2hX20FH89nhqrs0BKL7OwlQEsQPLt9kZx6dP5oDQhBeoQn.png)

3.  **Confirm & Train**: Check the links included in the sitemap.
    

![](https://staticfiles.gleap.io/ghelparticle/6EpKlpoJ2tiutdi5R9GPgm6VJ2C8YiLue69klwzlfC0OBKtwdycuDlTirmMDYXHia1Jy6YLvnw4.png)

**But, there are a few critical things to bear in mind:**

a. **Public access**: The pages on your site should be publicly accessible. The AI can't access data on pages that are behind a login or any other kind of access restriction.

b. **Ownership**: You must ensure that you have the necessary rights to use the site's content for training purposes. This might require permissions or licenses, depending on the content and source.

c. **Firewalls**: If your site is behind a firewall, you might have to temporarily disable it. This allows [Agent.so](http://Agent.so) to reach your site and use it for training.

Remember to respect all legal and privacy norms during this process.