Signal

When a tracker runs, it produces a Signal — a scored, uncertainty-adjusted assessment you can act on.

Signal Output

{
  "score": 7,            // 0-10 raw assessment
  "signal": "Positive",  // Uncertainty-adjusted action-oriented category
  "analysis": "..."      // Detailed explanation
}

---

Understanding Signals

Each tracker run goes through two stages:

1. Actor — the main AI agent analyzes the topic and produces a raw Score (0–10).
2. Critic — a second AI evaluates the Actor's work and produces an internal assessment.

The signal is derived from an Expected Score that blends the raw score with the Critic's internal assessment. When the Critic's confidence is high, the signal stays close to the raw score. When confidence is low, it regresses toward a prior — filtering out noise.

This means a high score alone isn't enough to produce an "Excellent" signal — the AI must also be confident in its assessment.

---

Signal Levels

Signal	Meaning
Excellent	Strong positive with high certainty — act confidently
Positive	Good outlook — worth acting on
Neutral	Average, uncertain, or needs more data — wait for confirmation
Negative	Warning sign — pay attention
Poor	Critical with high certainty — immediate action needed

---

Receiving Results

There are several ways to stay informed when your trackers produce new signals:

Method	Description
Console	View all results in real-time on your tracker's dashboard. Filter by signal, score, and date.
Email	Get an email summary each time a tracker completes a run. Enable per-tracker in notification settings.
Webhooks	Receive a POST request to your endpoint with the full signal payload. Great for automating workflows.
API Polling	Use GET /api/trackers/{id}/runs to fetch results programmatically. Supports sync mode for instant results.

Setting Up Notifications

In the Console, open a tracker → Settings → Notifications to configure email alerts or webhook URLs. You can also set these via the API using notification_config when creating or updating a tracker.