When a user asks about anomalies in their data, PyOD's od-expert skill auto-activates. The v3.2.0 skill encodes a master decision tree, top-10 critical pitfalls, and 11 adaptive escalation triggers. The shaded panels below the agent's turns show the skill's live decision-making.
od-expert.
| Detector | Raw score | Percentile |
|---|---|---|
| KNN | 304.13 | 100th |
| IForest | 0.15 | 99.9th |
| LOF | 3.41 | 99.8th |
engine.explain_findings:
| Feature | |z-score| | Raw value |
|---|---|---|
| insulin | 6.65 | 846 µU/mL |
| age | 2.19 | 59 yrs |
| glucose | 2.13 | 189 mg/dL |
| pregnancies | 0.84 | 1 |
Note: engine.explain_findings returns absolute z-score magnitudes; the raw values above are cross-checked manually to show direction. Extreme insulin (|z|=6.65), elevated glucose and older age — a metabolic-syndrome profile that warrants individual clinical review. Other top-flagged patients (#228, #247, #579, #177) each have their own contributing-feature ranking; insulin dominates several but is not a universal signature.
ADEngine session API is unsupervised in v3.2.x, so I would drop out of the session and call XGBOD directly on the classic fit / predict path:XGBOD later if the labels are validated.
RobustScaler first.state.analysis['consensus_analysis']['anomaly_ratio']). Close enough for unsupervised screening; adjust if you have domain knowledge.ADEngine session and calling XGBOD (classic fit / predict, pyod[xgboost] extra) typically lifts AUC 10–20 points over unsupervised.