Skip to main content
fanout

Simulation run on this device. Scenario values are not sent anywhere — the engine is fully local.

prompting studio · pro

Model Response Comparator

Line up responses side by side with rubric scoring.

Same prompt, three models — grade the spread.

Engine 1.0.0 · studio

Paste two or more responses separated by blank lines.

Method

  • Scores each response against a four-part rubric (specificity, structure, accuracy signals, concision), then recommends a default for the prompt class.
  • The rubric is heuristic — it rewards evidence and shape, not truth.

Keep going in prompting

prompting gamePrompt GauntletCan you keep the format under adversarial inputs?prompting studioPrompt LinterWhich words in this prompt are doing nothing?prompting studioStructured Output Schema StudioWhy does the model keep adding prose around your JSON?