Track prompt changes across versions with author, model, evaluation score, deployment status, diff context, and rollback points. This example brings Versions and Diff together so AI product teams can find the next task without losing context.
It includes representative records such as v24 · concise output format and v23 · added policy examples. Use the screenshot to study the layout, then adapt its components and product states to your own design system.

Table
New version
Table
Default, loading, empty, error, permission, success
Configurable product UI theme
Product teams need to new version while keeping versions, deployed and exceptions visible. The interface should show what changed and who should act next.
Versions → Diff → New version → Review outcome
Table, Versions, Diff, 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 versions and diff. People need to distinguish v24 · concise output format from v23 · added policy examples. Keep versions 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 version”. Make error recovery as clear as the happy path.
Related screen examples to explore next: Retrieval Playground, Evaluation Dataset, Knowledge Source Manager.
Design a prompt versioning screen inside our existing product. Use our current components, tokens and content language. Include Versions and Diff views, credible records like v24 · concise output format, and a clear “New version” action. Use our product permissions and show loading, empty, error and success states. Keep the output editable in Figma.