> ## Documentation Index
> Fetch the complete documentation index at: https://help.ascentialxai.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Chat from the side panel

> Send prompts, get responses, and control the conversation.

The **Conversation** tab is where you chat with the assistant. You need a provider connected and a model selected before sending messages.

## Send a message

Type your prompt in the composer at the bottom of the side panel and press **Enter** to send. The assistant responds using your selected model.

## Stop a response

Click **Stop** to cancel a running response. The partial response is discarded.

## Model requirement

A provider and model must be configured before you can send messages. If no model is selected, the composer shows a prompt to set one up.

## How chat works

Most prompts go directly to your selected model for a response. When you use a slash command like `/browser`, `/memory`, or `/scraper`, the assistant routes your request to the appropriate skill and returns the result in the chat. This happens automatically — you just see the response.