Use Zeno
One question in. One check out.
HTTP, MCP and Python run the same published model and return the same identity.
input
one question
many forecasts
zeno_check
MCP · HTTP · Python
output
forecast
range · warnings
01 · serving
Correction is earned.
Measured sources receive the selected model path. Others keep their reference unless experimental mode is requested.
Crypto price ranges
Zeno correction
+11.7%
Ensemble weather
Zeno correction
+5.6%
Deterministic weather
correction · no history
+6.2%
COVID-19 hospitalisations
correction · no history
+11.8%
Sea conditions
correction · no history
+3.2%
Prediction markets
reference kept
RSV
reference kept
FluSight
reference kept
ForecastBench
reference kept
Numinous AI forecasters
learn-only
02 · response
Read served_as first.
Every answer identifies the model revision, reference, distribution, uncertainty and any confident-forecaster warnings.
served_as
reference
forecast + range
warnings + identity