Test retrieval queries against connected knowledge with filters, top-k, reranking, source previews, and relevance feedback. This example brings Query and Sources together so AI product teams can find the next task without losing context.
It includes representative records such as Enterprise permissions policy and Billing edge cases. Use the screenshot to study the layout, then adapt its components and product states to your own design system.

Builder
Run query
Builder
Default, loading, empty, error, permission, success
Configurable product UI theme
Product teams need to run query while keeping top-k, sources and exceptions visible. The interface should show what changed and who should act next.
Query → Sources → Run query → Review outcome
Builder, Query, Sources, contextual actions, error recovery
Show constraints before adding blocks, keep a usable preview and protect unsaved changes as people test a different direction.
Pay attention to query and sources. People need to distinguish Enterprise permissions policy from Billing edge cases. Keep top-k 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 “Run query”. Make error recovery as clear as the happy path.
Related screen examples to explore next: Knowledge Source Manager, Prompt Versioning, Tool Connector Setup.
Design a retrieval playground screen inside our existing product. Use our current components, tokens and content language. Include Query and Sources views, credible records like Enterprise permissions policy, and a clear “Run query” action. Use our product permissions and show loading, empty, error and success states. Keep the output editable in Figma.