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

# Chat Overview

> An overview of chat in Jinba App Neo

Chat is the central screen of Jinba App Neo. Talk to an agent to ask questions or request work, watch the AI's progress in real time, and receive the results.

## Types of chats

| Type            | Description                                                                                                           |
| --------------- | --------------------------------------------------------------------------------------------------------------------- |
| **Agent chat**  | A chat bound to a specific agent. That agent's skills, connectors, knowledge, and memory are applied automatically    |
| **Ad-hoc chat** | A chat with no agent specified. It runs with the workspace default model and the default Skill (if one is configured) |

Selecting an agent via `@` in the composer or the "+" menu when creating a chat turns it into an agent chat.

## Screen layout

* **Sidebar** — New chat, Search (command palette), Agents, Flow, Configure (Skills, Knowledge, Connectors), and pinned / recent chats (grouped into Today / Yesterday / Last 7 days / Last 30 days)
* **Message area** — The conversation history. The AI's activity (thinking, running tools, and so on) also appears here
* **Composer** — Message input, file attachments, and the reference pickers
* **Workspace panel** — A side panel that previews one file at a time, with the chat's files, the console log, and — in an agent chat — that agent's configuration a tab away

## Basics

<CardGroup cols={2}>
  <Card title="Composing Messages and Attachments" icon="keyboard" href="/en/pages/jinba_app_neo/chat/composer">
    How to send messages, the reference pickers (@ / # / \[\[ and more), and file attachments
  </Card>

  <Card title="AI Activity and the Workspace Panel" icon="bolt" href="/en/pages/jinba_app_neo/chat/agent-activity">
    Reading the AI's progress, interrupting it, and inspecting deliverables and the console log in the preview panel
  </Card>

  <Card title="In-Chat Forms and Suggestions" icon="rectangle-list" href="/en/pages/jinba_app_neo/chat/interactive-cards">
    Flow input forms, multiple-choice questions, AI operation cards, agent setting proposals, and skill suggestions
  </Card>

  <Card title="Managing and Searching Chats" icon="folder-open" href="/en/pages/jinba_app_neo/chat/manage-chats">
    Pinning, renaming, deleting, cross-chat search, and in-chat search
  </Card>
</CardGroup>

## Models and chats

The model used in a chat is decided when the chat is created and **stays fixed within that chat**. To use a different model, start a new chat — or, when it is the agent's model that changed, switch this chat to the agent's new settings (below). You can check the current model on the model badge in the chat screen.

## When the agent's settings change mid-chat

An agent's configuration — system prompt, model, attached skills — is fixed when the chat's session starts, so editing the agent does not reach a conversation that is already under way. When that happens, a banner appears above the composer: "**This agent's settings were updated — this chat is still running on the previous configuration.**"

* "**Switch to the new settings**" starts a fresh session on the current configuration; it applies from your next message
* Switching makes the AI **forget this conversation's working context**. The visible history stays exactly as it is, but the AI no longer remembers what it had been working on
* You cannot switch while the AI is running — wait for the current reply to finish and try again

## Response language

The AI generally responds in **the language you write in**. An explicit request such as "answer in English" always takes top priority. The app's display language (Settings > Appearance > Language) is used as a fallback when the language cannot be determined from your input.

## When you hit your usage limit

Once you reach the monthly usage included in your workspace plan, sending messages is temporarily blocked and the reset date is shown. To raise the limit, talk to your workspace owner or contact support.

The limit is also checked while a reply is being generated: if a long run crosses it partway through, the run is stopped there and the chat shows "This response was stopped because you've reached this month's usage limit." Whatever the AI produced up to that point stays in the chat.