Telemetry

Engine health

Aggregate operational figures across every persisted run. Debate topics, context, follow-up text and feedback messages are never shown here.

runs in the last 7 days

100%

completed without a fallback

0.0

average retries per run

$0.33

estimated spend, all time

Step reliability26 recorded model calls

Stance scouts

no calls recorded

Pro and con arguments

100% ok · 0 fell back · 0 retries

Debate turns

100% ok · 0 fell back · 0 retries

Judge scorecard

100% ok · 0 fell back · 0 retries

Final verdict

100% ok · 0 fell back · 0 retries

Run volumelast 14 days

Aug 20Sep 2

Run status0 active

queued

framing

researching

debating

judging

complete

failed

partial

Model usageruns each model took part in

google/gemini-2.5-flash

openai/gpt-4.1

openai/gpt-5.5

Aggregate outputacross persisted runs

Total runs3

Completed2 · 67%

Evidence sources14

Debate turns18

Follow-up answers0

Model tokens157391

Feedback entries0

Latest activity 2026-09-01 23:35 UTC