waveguard_scan
Detect anomalies in any data type by sending normal examples and suspect samples in one API call. Returns per-sample scores, confidence, and explanatory features using GPU-accelerated wave physics.
Instructions
Detect anomalies in data using GPU-accelerated wave physics simulation. Fully stateless — send training data (normal examples) and test data (samples to check) in ONE call. Returns per-sample anomaly scores, confidence levels, and the top features explaining WHY each anomaly was flagged. Works on any data type: JSON objects, numbers, text, time series, arrays. No separate training step required.
Example: to check if server metrics are anomalous, send 3-5 normal readings as training, and the suspect readings as test.
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| training | Yes | 2+ examples of NORMAL/expected data. These define what 'normal' looks like. All samples should be the same type and shape. More samples = better baseline (4-10 is ideal). | |
| test | Yes | 1+ data points to check for anomalies. Same type/shape as training data. Each sample is scored independently. | |
| sensitivity | No | Anomaly threshold multiplier (default: 2.0). Lower = more sensitive (flags more anomalies). Higher = less sensitive. Range: 0.5 to 5.0. | |
| encoder_type | No | Data encoder type. Omit to auto-detect from data shape. Auto-detection works well for most data. |