The Signal Journal

Less noise.
More understanding.

Original guides to prediction markets, the platforms behind them, and the APIs and AI tools reshaping the conversation.

A market's headline probability leaves out the price, quantity, and timing assumptions that determine what an order could actually receive.

AI & agentsAugust 24, 2026

Design a research agent that preserves evidence, separates observations from inference, and lets a reviewer reconstruct every published forecast.

AI & agentsJuly 11, 2026

A practical framework for evaluating prediction bots without confusing an impressive simulation with a reliable trading system.

AI & agentsMarch 30, 2026

A convincing explanation is only the beginning. Learn how to record forecasts, calculate Brier scores, and test calibration without hindsight.

AI & agentsJune 25, 2025

Give AI a defined research task, a dated evidence set, and a reviewable output before asking it for a probability.

Build a research dataset you can explain: preserve contract rules, distinguish prices, track timestamps, and make missing data visible.

Platform guidesFebruary 15, 2025

Compare the same question across platforms by examining contract meaning, evidence, timing, prices, and the quality of your data.

Platform guidesDecember 14, 2024

A careful reading method for Kalshi event contracts, from thresholds and source documents to deadlines and order book observations.

Platform guidesDecember 1, 2024

Explore the relationship between events, outcome tokens, executable prices, and the rules that determine a Polymarket result.

Learn what an event contract measures, how to read a market price, and why the resolution rules deserve your first look.

What question should we explore next?

Send a topic, a correction, or a perspective worth discussing.