> For the complete documentation index, see [llms.txt](https://docs.kyso.io/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.kyso.io/search-and-discovery/searching-reports.md).

# Searching Reports

## Searching in Channels

In any channel you have access to, you can simply select which variables you want to filter by with Boolean selectors, similar to how Gitlab's search works. You can refine your search further with text input that will search by title and description content.

<figure><img src="/files/jFUkOEndfRDWQgAZwfQe" alt=""><figcaption><p>Metadata Selectors to Narrow Search</p></figcaption></figure>

## Global, Full-Text Search

Using Elastic Search, Kyso also indexes full-text on the report body, such that end users are able to search by the internal content of project reports, on all reports across all Organisations and Channels one has access to.

Simply enter your search query in the top navigation bar input box - Kyso's global search. You can enter keywords or longer-tail strings and Kyso will return matching results.

<figure><img src="/files/jFQEnkv3nthbQYLNZyQ5" alt=""><figcaption><p>Kyso's Global Search Page</p></figcaption></figure>

As you can see from the image, comments are also indexed and searchable. The conversations that insights inspire are just as important to maintain as the insights themselves.

Kyso ranks the most relevant results at the top of the list.

{% hint style="success" %}
Note that your search queries are saved to the url, which you can share as you would a Kyso report!!!
{% endhint %}

You can narrow full-text search queries even further by selecting specific metadata like channels, tags, authors, and more. You can even filter by file type. This allows the user to construct really complex search queries.


---

# 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://docs.kyso.io/search-and-discovery/searching-reports.md?ask=<question>&goal=<endgoal>
```

`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.