> For the complete documentation index, see [llms.txt](https://ask.birdie.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://ask.birdie.ai/core-concepts-and-entities/understanding-and-using-skye-in-birdie.md).

# Understanding and Using Skye in Birdie

## What is Skye?

Skye is an artificial intelligence assistant designed to help users navigate through insights and make informed decisions. While Skye strives to provide accurate and helpful information, it is continually learning and may not always have complete information. Users are encouraged to verify important details when necessary. Skye lives in a persistent side panel that you can open from its own tab in the sidebar or from the floating bird button, and it's available across Exploration, Areas, Opportunities, Initiatives, Manual Evaluation, Agent Feedback, and Disputes pages. You can also personalize the bird that represents Skye in your conversations.

![](https://2659701720-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FN7EEIMhL4xEKWM6BDyEL%2Fuploads%2Fgit-blob-e6848fdad429c6b3f986424d07901ac37c46ca13%2FSkye%20drawer.png?alt=media)

### Main Features:

* Discover Opportunities in Reported Problems: Skye generates a list of opportunities based on feedback about area problems, allowing them to be added by clicking "+Add".
* Explore and Refine Opportunities: Skye suggests new insights and allows deeper analyses related to the current opportunity, assisting in exploring specific solutions.
* Ask a Question: Allows the user to ask about patterns, recurring problems, causes of dissatisfaction, among others.
* Reference Linked Records: When Skye mentions an opportunity or initiative, it appears as a clickable link — hover over it to preview key details without leaving the conversation.
* Generate Reports: Skye can produce full digest-style reports as part of a conversation, rendered inline as cards you can open in a resizable, fullscreen panel.

### How to use Skye?

Skye is a versatile tool within Birdie that adapts to various contexts, enhancing your ability to extract and analyze customer feedback effectively. It offers flexibility in how you interact with it, allowing for both structured and unstructured engagements.

### Using Skye in Different Contexts

Skye's functionality adapts based on where you're interacting with it, and it responds dynamically to the filters you've applied. This adaptability allows Skye to present information that aligns precisely with your current focus, enhancing the relevance and specificity of the insights provided. For more detailed information on how to apply filters in Birdie, access the complete [documentation](/customer-intelligence/exploration-and-analysis/using-filters-in-birdie.md).

Beyond Exploration, Areas, and Opportunities (detailed below), Skye is also available on Initiatives, Manual Evaluation, Agent Feedback, and Disputes pages, adapting to the context of each.

{% tabs %}
{% tab title="Exploration Page" %}
Skye on the Exploration Page

On the Exploration Page, Skye serves as a powerful tool to delve into customer feedback. It enables you to filter and search through vast amounts of data, facilitating the discovery of actionable insights. This feature is particularly useful for identifying trends and patterns in customer sentiment.
{% endtab %}

{% tab title="Areas" %}
Using Skye in Areas

Within defined areas, Skye immerses itself in the established context, enabling a deep dive into particular segments of your customer base or product lines. This immersion facilitates a nuanced understanding of feedback and opportunities within that area. For more detailed information about areas of interest, refer to the [documentation](/core-concepts-and-entities/areas.md).

Skye offers several pathways to explore opportunities and insights inside areas:

* Discover Opportunities in Reported Issues: Identify potential opportunities based on customer feedback related to reported issues, allowing them to be added by clicking "+Add".
* Discover Requested Features: Highlight opportunities stemming from customer requests for new features.
* Ask a Question: Engage directly with Skye to inquire about specific data or insights within the area.
  {% endtab %}

{% tab title="Opportunities" %}
Using Skye in Opportunities

When engaging with opportunities, Skye immerses itself in the context of potential improvements or innovations identified through customer feedback. This approach facilitates a nuanced understanding of feedback and opportunities within that opportunity. For more detailed information about opportunities, refer to the [documentation](/customer-intelligence/opportunities.md)

Skye offers several pathways to explore opportunities and insights within opportunities:

* Refine an Existing Opportunity: Delve deeper into identified opportunities to uncover more granular insights, allowing for the development of more targeted and effective strategies.
* Discover Opportunities in Reported Issues: Identify potential opportunities based on customer feedback related to reported issues.
* Ask a Question: Engage directly with Skye to inquire about specific data or insights within the opportunity.
  {% endtab %}
  {% endtabs %}

### Chat Features

Within the chat interface with Skye, users have access to several features designed to enhance workflow and analysis efficiency.

* Manage Conversations: keep multiple named conversations in the sidebar, rename them inline, and resume any past conversation — including in fullscreen. Your active conversation stays open even as you navigate between pages.
* See Skye's Thought Process: while Skye is working on a complex answer, the steps it's taking are shown progressively instead of a blank loading state.
* Copy response (available after each Skye message): Copies Skye's response, facilitating documentation and sharing of analyses.
* Add Specific Context: Filter feedback by origin or type (e.g., CSAT, Tickets, Author ID). Select desired filters and click "Save Changes."\
  Note: more specific filters may reduce analyzed feedback volume.
* Conversation Memory Meter: a running indicator of how much of the conversation's context is being used, so you know when it's time to start a new conversation.
* Personalize Skye: pick the bird that represents Skye by clicking on the bird right in the chat footer.

## Getting Started with Skye

To start using Skye in Birdie, open it from its tab in the sidebar or from the floating bird button available on supported pages. Start a new conversation, or resume a previous one from the sidebar list. Engage with Skye by asking questions, exploring generated reports, and customizing settings like your preferred bird and context filters. Utilizing these functionalities will enhance your analytical processes and tailor your experience to meet your specific needs. Start interacting with Skye today to fully harness its potential!

![](https://2659701720-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FN7EEIMhL4xEKWM6BDyEL%2Fuploads%2Fgit-blob-d26357c9b4356a52ed523cc8ee5ed0e57bbf3d39%2FSkye-tab.png?alt=media)


---

# 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://ask.birdie.ai/core-concepts-and-entities/understanding-and-using-skye-in-birdie.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.
