Skip to main content

Chat

Chat is where you work with your agents. It's a fast, live web interface — a window into the agent's work as it unfolds.

Watch the work unfold​

When an agent works, everything streams to your screen in real time:

  • Text and reasoning as the agent thinks through the problem.
  • Tool calls as it runs them — searching, editing, fetching, querying.
  • File edits as they're made.
  • Plans and to-do lists that update live as the agent checks items off.
note

Plans, live to-do checklists, and sub-agents are capabilities of the Claude Code and Codex engines. The lighter direct engine streams text and tool calls but doesn't show plans or to-dos. See AI Engines.

Attach files and images​

Drop a file or image right into the chat — photos, PDFs, Office documents, text, data files, audio, and video are all supported. You can attach by dragging in, picking from the file browser, or pasting a path. (HTML and SVG uploads are blocked for safety.)

Rich results inline​

Agents don't just reply with text. Right in the conversation you'll see:

  • Image galleries for pictures an agent produces or shows.
  • Interactive artifacts — charts, tables, calculators, and small tools the agent builds as real, live UI. See Artifacts.
  • Live document previews for PDFs, Word, Excel, and PowerPoint — scroll, zoom, edit, and download without leaving the chat.
  • Media players for audio and video, with full playback controls.
  • Downloadable files as clickable cards.

Approvals in the flow​

Depending on the permission mode, an agent pauses before sensitive actions — editing files, running certain commands, using a tool — and asks you right in the chat. Click Allow or Deny and it continues. Switch modes any time — from approving each sensitive step to fully autonomous. Claude Code also offers a read-only Plan mode for investigate-first work.

Switch model mid-chat​

Change the model from the dropdown without losing your place — try a question on a faster model, then switch to a more capable one for the heavy lifting, mid-conversation. You switch among the models of the chat's current engine; to run on a different engine, start a new chat (an agent can offer more than one).

Work across many conversations​

  • Start a new chat any time, with any agent you have access to.
  • Resume past conversations from the sidebar, grouped by recency — they pick up right where you left off, even after a server restart.
  • Search across all your chats, or within one chat, to find that thing you discussed.

Talk to your agents​

Prefer to speak? The dashboard supports voice input and spoken replies, including a hands-free voice mode. See Voice.

Next steps​

  • Tasks → — put an agent's work on a schedule.
  • Memory → — help agents remember across conversations.
  • Voice → — speak to your agents and hear them reply.
  • Permissions → — control what agents do on their own.