Work with an AI assistant in persistent conversations with files, sources, model context, history, and clear handoff between threads. This example brings Chats and Projects together so AI product teams can find the next task without losing context.
It includes representative records such as Launch positioning review and CRM redesign exploration. Use the screenshot to study the layout, then adapt its components and product states to your own design system.

Inbox
New chat
Inbox
Default, loading, empty, error, permission, success
Configurable product UI theme
Product teams need to new chat while keeping chats today, files attached and exceptions visible. The interface should show what changed and who should act next.
Chats → Projects → New chat → Review outcome
Inbox, Chats, Projects, contextual actions, error recovery
Keep the current item close to its history, owner and urgency. Put the next action on the record rather than making people open several panels.
Pay attention to chats and projects. People need to distinguish Launch positioning review from CRM redesign exploration. Keep chats today visible, especially when a record changes owner or status.
Before this screen reaches handoff, verify keyboard focus, empty and permission states, and what happens after someone chooses “New chat”. Make error recovery as clear as the happy path.
Related screen examples to explore next: Agent Builder, Tool Connector Setup, Knowledge Source Manager.
Design a ai chat workspace screen inside our existing product. Use our current components, tokens and content language. Include Chats and Projects views, credible records like Launch positioning review, and a clear “New chat” action. Use our product permissions and show loading, empty, error and success states. Keep the output editable in Figma.