
Probe console
Dopamine Ultra 1 ・ 10M contextBuilder-chosen suite. I chose one probe per capability band — context, planning, build, quality, ship and long-context limits — and a continuation probe that pushes the prompt length. None of them purchase credits or subscribe; the console only records what the provider returns.
Recalled the goal statement across the session.
Produced architecture, tasks and milestones.
Returned frontend, backend and API routes.
Returned unit and integration test files.
Returned Dockerfile and Helm chart.
Continued after a long prompt without interruption.
Results are recorded against run run-2026-02-11-a. Open the results view to read every outcome and the pay-wall verdict.
Open results view
Dopamine Ultra 1 ・ 10M contextprobe target · 8080.ai
Send agent probes to 8080.ai and see the results and any credit wall.
Every run goes to the provider with the current model selection. The suite is chosen for you: seven categories, 47 probes, each written to surface a capability or a limit rather than a feature tour.
Counts are the probes planned per category; nothing here reports a run. Results and any credit-wall evidence appear on Probe Results once a run has executed.
No comments yet. Be the first!