Model Playground

Test prompts against model and parameter choices with input, output, latency, token use, and comparison context visible. The screen connects Playground and Models so platform and engineering teams can find the “Run prompt” action while checking model and temperature.

Use this reference when you need to design this workflow inside an existing product. The example includes practical records such as System instructions and User input, rather than an empty visual shell.

Model Playground
Use this template in Figr

Template facts

Screen

Form

Primary action

Run prompt

Pattern

Form

State

Default, loading, empty, error, permission, success

Design system

Adaptable product UI theme

What this screen helps users do

Platform and engineering teams need a clear “Run prompt” action without losing sight of model, temperature and the affected records. Keep the decision and its outcome clear before moving to the next task.

Key elements

  • Primary action: Run prompt is clearly available where the task happens.
  • Main view: Playground keeps the starting point obvious.
  • Connected view: Models supplies nearby context.
  • Metric: Model is visible with a meaningful value.
  • Another signal: Temperature helps people judge what to do next.
  • Representative record: System instructions makes the example specific.
  • Second record: User input shows the pattern works beyond one item.

States worth designing

  • Missing required details; show what people can do instead of leaving a blank panel.
  • Loading playground without changing the layout unexpectedly.
  • Invalid or conflicting entry; explain the problem and preserve work.
  • Permission denied for models; clarify who can continue.
  • Success after choosing Run prompt; confirm the result and the next step.
  • Network or data refresh failure; offer a retry without losing context.

Where this screen sits in the flow

Playground → Models → Run prompt → Review outcome

Patterns used

Form, Playground, Models, Presets, accessible states, contextual actions

Why these choices work

Put requirements beside each field and show validation near the source of the error. Keep entered details if saving fails.

In this design, people should be able to compare System instructions with User input. Make model clear, then use temperature to explain whether the next step needs attention.

Before handing this to a designer or engineer, check keyboard focus, error copy, permissions and what happens after they choose the “Run prompt” action. The happy path alone is not enough.

Related UI examples: Feature Flags, Prompt Library, Logs Explorer.

Start from this in Figr

Design a model playground screen for our existing software product. Use our real design-system tokens, components and product language. Show Playground and Models, include believable records such as System instructions, and make run prompt easy to find. Map loading, empty, failure, permission and success states before you create editable high-fidelity screens.

Open Figr