# Training Data

Pylon's many AI features, like [ask-ai](https://docs.usepylon.com/pylon-docs/platform/ask-ai "mention"), [copilot](https://docs.usepylon.com/pylon-docs/support-workflows/issues/copilot "mention") for Issues, [ai-agents](https://docs.usepylon.com/pylon-docs/ai-agents "mention"), [#federated-search](https://docs.usepylon.com/pylon-docs/knowledge-base/search#federated-search "mention"), and more all benefit from having access to more information. 

By default, they have access to your past Pylon issues and your Pylon Knowledge base. Make them even more powerful by connecting any external sources of knowledge you have!

## Setup

1. Go to the [Training Data](https://app.usepylon.com/settings/ai-controls/training-data) page in Settings and click "Import Data".
2. Select a method of importing data and follow the instructions.

<figure><img src="https://982123570-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F9hXBoCTTNw5flARlUVJf%2Fuploads%2FbnknT1yk38H5wuh4Juf9%2FScreenshot%202026-03-09%20at%201.56.52%E2%80%AFPM.png?alt=media&#x26;token=add5d364-5bfb-4576-90f4-5a008214b71c" alt=""><figcaption></figcaption></figure>

* Your Pylon knowledge base and past issues will be enabled by default and reindexed **live**
* Public URLs to individual webpages or a base url to crawl that will be reindexed every 7 or 30 days depending on your Pylon plan. Examples may include:
  * Public-facing documentation not hosted by Pylon
  * Public Google docs
  * Public GitHub repos
  * Your marketing website or pricing page
* Give Pylon a few moments to automatically scrape and index all your content

This data is now available to power all your AI features!


---

# Agent Instructions: 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:

```
GET https://docs.usepylon.com/pylon-docs/platform/training-data.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
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.