Chat

The composer has the profile, the model, Run on, Effort, and Memory. Model Auto picks an installed model for each message: a quick question stays on a model that is already loaded, coding goes to a coding model, a question about current information or a task on this computer goes to a model that can use tools, and a question about your files or knowledge prefers a larger model. A question about what one of your specialized AIs was trained for goes to that AI. Choose a model yourself to keep it for the chat.

Effort sets how much care an answer gets. Fast answers in one go. Balanced plans requests with several parts and reads a page for each look-up. Thorough reads more, checks figures twice, and uses the largest model that fits. Auto keeps quick questions fast and gives questions about your data, and requests with several parts, more care. Your choice is remembered. Get more careful answers covers Effort with reasoning models, a profile's Reasoning level, and comparing drafts.

Attach documents (including Word documents and PowerPoint decks), spreadsheets, PDFs, and code files with the paperclip, by dropping them on the message box, or by pasting. The answer cites the file, and later questions in the chat can still use it. Pictures and video are shown to a model that can see, and audio can be transcribed. Ask for a file, such as a spreadsheet of prices, a Word document, or a page saved as hours.html, and the answer comes with a download; spreadsheets are real .xlsx workbooks. A scanned PDF is read with text recognition, which takes a moment after you attach it, the first time only.

Under each answer, Sources lists the web pages, knowledge passages, files, and memories it used, and What I did lists the model that answered and why, the searches and pages read, and anything that went wrong. A request with several parts, such as comparing three products, shows a checklist while its parts run. Figures are checked against the sources before you see the answer, and a figure that could not be confirmed is called out below it. A notice also appears when a small model answered a question about your data, or when the model that answered is smaller than the one that failed.

Stop ends everything working on the answer, including web look-ups and paired computers, and keeps what was already written. The context ring beside Send shows how much of the model's window the conversation uses. When a long chat passes half the window, older messages are summarized after the reply; they stay saved.

History lists your chats by date; each one's menu renames, pins, or deletes it. To delete several, choose Select, tick the chats (Shift-click picks a range, and Cmd- or Ctrl-click a chat to start choosing), and choose Delete. Select all takes the chats a search shows. One confirmation covers them all, and Undo brings them back for 10 seconds. Settings → History deletes chats last used more than 30, 90, or 365 days ago, keeping pinned ones, and shows how many before you confirm.