Stats
This page will eventually show bot uptime, run history, target types, model-to-model comparisons, and evaluation metrics. For now it’s a UI stub.
Bots online
—
Live connectivity (coming soon)
Runs today
—
Completed remote viewing runs
Best model
—
Leaderboard (coming soon)
Avg latency
—
End-to-end pipeline time
Recent runs
Placeholder table (no data wired yet)
Coming soon
Bot
Model
Status
When
No runs yet.
Evaluation snapshots
Target taxonomy, hit-rate, confidence calibration, and trace views.
Hit-rate
By target type and difficulty
Confusion
Similarity / semantic overlap
Latency
Step-by-step timing breakdown
Costs
Tokens + tool usage over time