Problem
People need to read the assistant’s answer while looking at the work it describes. A dialog covers that work, and a separate page makes them switch back and forth.
Solution
Place the assistant in a panel beside the workspace. Let it use the open document or selected content, and show what it can see. Give people a way to change that selection.
Let people resize and close the panel, and remember their choice. Provide a keyboard shortcut to open and close it. On small screens, let people switch between the conversation and their work without losing their place.
When an answer belongs in the document, provide an insert action. Make the destination clear before changing the document.
Use when
The assistant needs access to the current work, and people need more than one exchange to complete a task.
Don’t use when
The interaction is a single act on a single object. A rewrite, a summary, or a rename is better served by an inline control, and opening a panel for it costs more screen than the task is worth.
Trade-offs
The panel reduces the space available for work. Keeping a conversation open across documents is convenient, but its context can become unclear. Show when the document or selection changes so people know what the next answer will use.
Checklist
- Does the panel know what the viewer is looking at, and does it say so?
- Can the viewer change what it can see?
- Is it resizable, and is the size remembered?
- Is open and close the same keystroke?
- Does the conversation survive navigating to another document, and should it?
- Is there a one-click path from an answer into the document?
- What does this become at a phone width?
- Does the panel push the content or overlay it?
- Where does the history of these conversations live?
- Does it reopen uninvited after being dismissed?
Compare
Claude keeps the conversation in the main column and pushes generated documents into the side panel, inverting the usual arrangement so the artifact takes the space rather than the chat. Notion binds its panel to the current page and pulls extra context through @-mentions. Scope gets typed rather than inferred. Microsoft Copilot in an Office application scopes to the open file and the tenant, where the panel’s hardest job is explaining which of those two it is answering from. Figma puts the assistant against the canvas selection instead of a document, so the panel’s context is a set of layers and the answers are structural rather than textual.
Related
Scoped context shows what the assistant can access. Inline assist handles a quick change to selected content. AI entry point helps people find the assistant.
Artifact panel gives generated content its own workspace. Conversation history keeps earlier conversations available.