Scoring

When a tracker runs, it produces a scored result — an evidence-based assessment you can act on.

Run Result

{
  "score": 72,             // 0-100 integer
  "insight": "..."         // Detailed explanation
}

---

Understanding Scores

Each tracker run produces a score (0–100 integer) and an insight (evidence and reasoning).

The AI agent sees the previous run's score and insight, then gathers fresh evidence via tools. If nothing has changed, the score stays close to the previous value. If new information surfaces, the score adjusts — and the insight explains what changed.

How Modes Affect Quality

Mode	How It Works
Basic	Single-pass analysis with quality gate. A separate Critic AI evaluates how well the score change is justified and dampens unjustified jumps. Fast and cost-effective.
Advanced	Multi-perspective analysis with iterative refinement. The Critic evaluates each iteration and provides structured feedback. More thorough.
Super	Comprehensive research-grade analysis with extensive Critic iterations. Highest depth and reliability.

All modes include a quality gate that dampens unjustified score changes — if the evidence doesn't support a big move, the score stays closer to the previous value. Higher modes additionally use Critic feedback to iteratively refine the analysis.

Score Stability

Scores are designed to converge when the underlying situation is stable:

• No new information → score stays close to the previous value
• New information → score adjusts, and the insight explains the change
• Higher modes → faster convergence due to deeper analysis

---

Score Distribution

Scores are grouped into 20-point range buckets for distribution analysis:

Score Range	Meaning
80 – 100	Strong positive with high certainty
60 – 80	Good outlook — worth acting on
40 – 60	Average, uncertain, or needs more data
20 – 40	Warning sign — pay attention
0 – 20	Critical with high certainty — immediate action needed

---

Receiving Results

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

Method	Description
Console	View all results in real-time on your tracker's dashboard. Filter by score and date.
Email	Get an email summary each time a tracker completes a run. Enable per-tracker in notification settings.
Webhooks	Receive a run.completed POST request to your endpoint with the full result 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.