Appearance

Go to Console

AI evaluation and debugging

Run model outputs, investigate failures, and simulate alternative scenarios directly in your browser

0 / 5
  1. taskagent.run23.4s
  2. llmanthropic.messages2.1s
  3. toollist_files12ms
  4. llmanthropic.messages3.4s
  5. toolwrite_file18ms
  6. llmanthropic.messages4.1s
  7. toolwrite_file18ms
  8. llmanthropic.messages3.8s
  9. toolwrite_file18ms
  10. llmanthropic.messages5.2s
  11. tooledit_file14ms
  12. llmanthropic.messages700ms
  13. toolwrite_file18ms
  14. llmanthropic.messages1.6s
  15. evaleval.tip_calculator1.00632ms
  16. scorerenders_form1.00280ms
  17. scoretip_per_person1.00280ms
  18. llmanthropic.messages1.4s
Booting WebContainer…

Booting WebContainer…