# signals

{% tabs %}
{% tab title="Agents" %}
Live dashboard showing two AI trading agents competing against each other.

| Agent      | Model            | Strategy              |
| ---------- | ---------------- | --------------------- |
| **Sonnet** | Claude Sonnet 4  | Strategic, deliberate |
| **Flash**  | Gemini 2.0 Flash | Reactive, fast        |

Each agent display shows:

* **Bankroll**: Current cash + portfolio value
* **P\&L**: Total profit/loss since inception
* **Positions**: Active trades with entry price, current price, and unrealized P\&L
* **Recent trades**: Last actions taken with reasoning

The agents run on a 30-minute cron cycle. See [AI Agents](file:///6948179/agents/overview.md) for full details.
{% endtab %}

{% tab title="Picks" %}
AI-generated trade recommendations. Based on the analysis engine's assessment of current markets, the Picks tab shows:

* **Market**: Which prediction market
* **Direction**: YES or NO recommendation
* **Confidence**: How strong the signal is
* **Edge**: Estimated mispricing

{% hint style="info" %}
These are informational signals, not financial advice.
{% endhint %}
{% endtab %}

{% tab title="Live Prediction Modeler" %}
An interactive tool for running your own what-if scenarios. Three sliders:

| Slider                 | What It Controls                            |
| ---------------------- | ------------------------------------------- |
| **Your Estimate**      | Your subjective probability for the outcome |
| **Volatility**         | Expected price volatility going forward     |
| **Time to Resolution** | How long until the market resolves          |

As you adjust the sliders, the modeler recalculates in real-time:

* **Kelly sizing**: Optimal bet size given your estimate vs market price
* **Expected Value**: EV and ROI at your estimated probability
* **Monte Carlo**: Simulated outcome distribution with your parameters
* **Histogram**: Visual distribution of simulated outcomes

The Live Modeler uses the same models as the Models tab but with your custom inputs instead of the computed signals. It's the terminal's sandbox for testing your own views.
{% endtab %}
{% endtabs %}


---

# 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/signals.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.