# README

**A Bloomberg-style intelligence terminal for prediction markets.**

YESNO turns raw Polymarket data into actionable trading intelligence. Seven panels. Eleven quantitative models. Two AI agents trading live. One MCP server that brings it all into your AI workflow.

**Live at <https://yesno.events>**

***

## What You Get

* **Real-time market scanner** with sorting, filtering, and sector classification across 8 categories
* **Composite probability engine** that synthesizes 11 independent signals into a fair value estimate
* **Full Kelly Criterion suite** including Half Kelly, Quarter Kelly, and Empirical Kelly (Becker 2025)
* **Monte Carlo simulation** with bounded random walk and configurable parameters
* **Order book depth visualization** including 3D wave surface rendering
* **AI-powered analysis** at three tiers (Scout, Analyst, Strategist) with real-time news integration
* **Two AI trading agents** (Claude Sonnet 4 vs Gemini Flash) competing with live bankrolls
* **9 enriched signal categories** computed from cross-referenced market data
* **Bias zone detection** identifying longshot and favorite bias
* **Whale tracking and smart money signals** from large trade flow analysis
* **Sector barometers** for Politics, Crypto, Sports, Economy, Geopolitics, Tech, Culture, Science
* **MCP server** with 8 tools, 2 resources, and 2 prompts for AI integration
* **Calibration engine** with presets and per-parameter tuning
* **Live Prediction Modeler** for interactive what-if scenarios

## Who It's For

| Audience                      | Use Case                                                               |
| ----------------------------- | ---------------------------------------------------------------------- |
| **Prediction market traders** | Edge detection, position sizing, portfolio signals                     |
| **Researchers & analysts**    | Quantitative models, probability calibration, bias detection           |
| **AI/LLM developers**         | MCP integration to bring live market intelligence into any AI workflow |
| **News & politics followers** | Real-time sentiment tracking across sectors                            |
| **Curious observers**         | Explore what the crowd thinks will happen next                         |

## Terminal Layout

```
+------------------+-------------------+------------------+
|     DEPTH        |     MARKETS       |      INTEL       |
| Book/Chart/      |  Live table with  | News/Comments/   |
| Models/3D/       |  YES%, volume,    | Holders/Dates    |
| Calibrate        |  sectors, search  |                  |
+------------------+-------------------+------------------+
|     SECTORS      |      FLOW         |    ANALYSIS      |
| 8 sector cards   | Whale trades,     | AI verdict,      |
| with barometers  | trade feed,       | intelligence     |
|                  | leaderboard       | brief, deep dive |
+------------------+-------------------+------------------+
|                  |     SIGNALS       |                  |
|                  | Agents, Picks,    |                  |
|                  | Live Modeler      |                  |
+------------------+-------------------+------------------+
```

## Key Differentiators

1. **Not just data, intelligence.** Raw odds are everywhere. YESNO layers quantitative models, AI analysis, and cross-signal synthesis on top.
2. **Transparent methodology.** Every model is documented. Every signal is explained. You see exactly how the composite probability is calculated.
3. **Calibration is yours.** Don't trust default weights? Adjust them. Conservative, Balanced, or Aggressive presets, or tune every parameter yourself.
4. **AI agents with skin in the game.** Two AI models making real trades on a schedule. Watch their reasoning, track their P\&L, learn from their decisions.
5. **MCP-native.** The first prediction market terminal designed to plug directly into Claude, Cursor, or any MCP-compatible AI tool.
6. **Free and open source.** Self-host it. Fork it. Build on it.

## Quick Links

* [Getting Started](/yesno-docs/getting-started/overview.md)
* [Terminal Panels Guide](/yesno-docs/terminal/markets.md)
* [Model Documentation](/yesno-docs/composite-probability.md)
* [MCP Server Setup](/yesno-docs/mcp-server/setup.md)
* [API Reference](/yesno-docs/terminal-apis.md)
* [Self-Hosting](/yesno-docs/self-hosting/setup.md)


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://yesno-1.gitbook.io/yesno-docs/readme.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.