> For the complete documentation index, see [llms.txt](https://documentation.astera.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://documentation.astera.com/astera-studio/chat/chat-ui-walkthrough.md).
# Chat UI Walkthrough
Chat is the primary way you interact with Astera Studio. You ask, the AI responds — but Chat is more than a conversation. It can access your workspace artifacts, run tools, generate reports, build dashboards, clean and transform data, and stream the result back to you live. Every answer can become an artifact you save, edit, share, or schedule.
### Starting a Conversation
The message input lives at the bottom of the chat.
1. Click into the input and type your question or instruction.
2. Type @ at any point to inline-reference a file, draft, skill, or connection. A picker opens; choose an item and it appears as a chip in your message.
3. Click the + button on the left to attach references via menu instead.
4. Click the model dropdown to change the model for this chat. The picker is described below.
5. Click the teal send arrow on the right or press Enter to send your message.
### Choosing a Model
Each chat runs on a language model of your choice. By default, the chat uses your *Claude Sonnet 4.6*; you can change it for a single chat or set a new default for all future chats.
1. Click the Default Model dropdown at the bottom-left of the message input. The picker opens above the input.
2. Type into the search box to filter the list, or click a provider icon on the left rail (OpenAI, Anthropic, Google, custom) to narrow by provider.
3. Click a model to use it for this chat. The dropdown updates to show your selection.
### Setting your default model
If a particular model is what you reach for every time, pin it as your default.
1. Hover the row of the model you want as default. A pin icon and an info icon appear on the right of the row.
2. Click the pin. The tooltip Set as my default confirms the action.
3. From now on, Default Model at the top of the picker resolves to the model you pinned, across every chat.
{% hint style="info" %}
**Note:** The default you pin is your personal default. Other users in the same workspace are unaffected.
{% endhint %}
#### Per-chat vs per-message
The model you pick in the picker applies to the active chat — it sticks across messages in the same conversation. If you start a new chat, it resets to your pinned default. To use a different model just for one question, change the picker before sending and change it back afterwards.
### Chat History
Every chat you start is saved, so you can come back to any conversation. The chat history sidebar keeps the list ready for you.
* Start New Chat — opens a fresh greeting screen.
* Recent Chats — your conversations, newest first.
* Search — filter the list by chat title.
* Inline rename — pencil icon on a chat row to edit the title.
* Delete — cross icon on a chat row, with confirmation.
---
# 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://documentation.astera.com/astera-studio/chat/chat-ui-walkthrough.md?ask=&goal=
```
`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.