Manage documents, websites, databases, and connected apps used as AI knowledge with sync status, scope, freshness, and ownership. This example brings Sources and Collections together so AI product teams can find the next task without losing context.
It includes representative records such as Product documentation and Support knowledge base. Use the screenshot to study the layout, then adapt its components and product states to your own design system.

Table
Add source
Table
Default, loading, empty, error, permission, success
Configurable product UI theme
Product teams need to add source while keeping sources, healthy and exceptions visible. The interface should show what changed and who should act next.
Sources → Collections → Add source → Review outcome
Table, Sources, Collections, contextual actions, error recovery
Prioritize columns that help people act. Keep filters when readers drill into details and return; show who owns each unresolved exception.
Pay attention to sources and collections. People need to distinguish Product documentation from Support knowledge base. Keep sources 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 “Add source”. Make error recovery as clear as the happy path.
Related screen examples to explore next: Tool Connector Setup, Retrieval Playground, Agent Builder.
Design a knowledge source manager screen inside our existing product. Use our current components, tokens and content language. Include Sources and Collections views, credible records like Product documentation, and a clear “Add source” action. Use our product permissions and show loading, empty, error and success states. Keep the output editable in Figma.