The part nobody else publishes
Every call we make, scored in public.
You are deciding whether to let our signals move your money. So you get the whole record: how often we were right, how often we were wrong, and how often we said we did not know. Computed from what we actually sent, with nothing left out.
Wicks emitted
—
since launch
Driver unknown
—
honest no calls
Verdict wrong
—
published, not hidden
Median lead
—
cause before mid
Figures go live with the feed. They are calculated from what we actually sent you, never typed in by hand, and this page shows them whether they flatter us or not.
Methodology
How the number is produced.
The record is only worth something if you can check how it was made and reproduce it.
Outcomes recorded at three horizons
For every wick we store the mid at five, fifteen and sixty minutes afterwards. The reaction verdict is judged against those, not against a later narrative.
Computed from the archive, not asserted
The counts on this page are derived from the same stored events subscribers received. The published total must equal the archive total; that equality is a tested requirement.
Nothing filtered out
No category of wick is excluded from the computation to improve the figure. Unknown drivers are counted as what they are, not dropped.
Reproducible by replay
Anyone subscribing can replay our history and regenerate these numbers themselves. If we were shading the figures, you would be able to prove it.
Why publish it at all
Because you should never take our word for it.
Anyone can claim their signals are good. A published, reproducible record lets you verify it before you risk anything, and lets you size your positions on measured accuracy instead of a sales pitch. A year from now this page will be the most valuable thing we own, and it belongs to you as much as to us.
Your agent is already watching the price. Give it the reason.
Start free. Real time from the first minute, five events an hour. One key and eight lines of code.
No card. No login. No dashboard.