> 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/product-updates-changelog/skye-2.0-whats-new.md).

# Skye 2.0: What's New

Over the past few months, Skye — Birdie's AI assistant — has gone through its biggest transformation yet. What started as a simple chat window has grown into a persistent, personalized, context-aware assistant that follows you across the platform. Here's everything that's new.

## A New Home for Skye

Skye now lives in a dedicated side panel instead of a pop-up modal, so you can keep your conversation open while you keep working on the page behind it.

* **Always within reach**: open Skye from its tab in the top left area of the sidebar, or from the floating bird button in the bottom right corner of various pages.
* **More places to ask**: Skye is no longer limited to Exploration and Opportunities. It's now available on several other pages like Manual Evaluation, Agent Feedback, Disputes, and Initiatives, with more on the way.

## A Refreshed Conversation Experience

The conversation itself has been redesigned end-to-end to feel clearer and more responsive.

* **New welcome screen** with a cleaner first impression when you start a chat.
* **See Skye's thought process**: complex answers now show the steps Skye is taking to get there, so you can follow what it is doing while it works.
* **Smoother scrolling**: your question is automatically brought into view the moment you send it.
* **Loading responsiveness** while a previous conversation is being restored, you can see the action happening.
* **Strength-discovery prompts**: Skye can now proactively suggest strengths worth exploring, not just opportunities.

## Make Skye Your Own

* **Pick your bird**: choose the avatar that represents Skye in your conversations from a picker accessible right from the chat.
* **A bird with personality**: Skye's footer icon now animates while it's thinking and responding, giving the whole experience a bit more life.

## Conversations That Remember

Skye moved from a single, disposable chat to full conversation management:

* **Multiple named conversations**, listed in a sidebar (accessible from the top left) so you can pick up where you left off.
* **Rename conversations** inline to keep them organized.
* **Resume instantly**: reopen any past conversation, in fullscreen if you like, right from the sidebar.
* **Stays open across navigation**: switching between entities or pages no longer closes your active chat.
* **A memory meter** in the chat input shows how much of the conversation's context is being used, so you know when it's time to start fresh.

## Smarter Citations & Links

Skye's answers are now easier to verify and explore:

* **Clickable references**: when Skye mentions an opportunity or initiative, for example, it's now a real link.
* **Hover previews**: hovering over a linked entity shows a preview card with key details, without leaving the conversation.
* **Graceful fallback**: if a cited item has since been deleted or archived, Skye tells you clearly instead of showing a broken link.

## Rich Reports, Right in the Chat

Skye can generate full digest-style reports as part of a conversation, and they now feel like a native part of the product:

* Reports render as **artifact cards** directly inline in the chat.
* Open any report in a **resizable, fullscreen panel** for a closer look.
* The most recently generated report **opens automatically**, so you don't have to hunt for it.

## Transparency on Usage

* A running **memory/usage meter** in the chat itself.
* A new section under **Settings → Usage** that shows how much of your organization's Skye usage has been consumed.

## Behind the Scenes

A lot of the work over the past three months focused on making Skye's answers more reliable and relevant, even if you never see it directly:

* Skye is better at staying on topic and declining requests that are out of scope.
* Responses are now aware of which product area you're asking from (Customer Intelligence or Frontline Intelligence), so answers are tailored to that context.
* Error handling has been significantly improved, with clearer recovery when a connection drops or a conversation can't be found.

{% hint style="info" %}
Some of these improvements are rolling out gradually behind feature flags. If you don't see a specific capability yet, it may be on its way to your organization soon.
{% endhint %}

{% hint style="warning" %}
Skye has its own way to understand your questions, call tools to retrieve information and prepare the answers it provides. Asking the same question in a different environment like Claude or ChatGPT will not necessarily reproduce the same result, and vice-versa.
{% endhint %}

Stay tuned — Skye is only getting started.


---

# 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/product-updates-changelog/skye-2.0-whats-new.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.
