MeshAI’s ML engine runs four detection algorithms every 5 minutes: cost spikes, reliability decay, behavioral drift, and security threats. Detected anomalies are surfaced via the SDK and dashboard.
list_anomalies()
List anomalies for your tenant, optionally filtered by status, type, or agent.
anomalies = client.list_anomalies(
status="open",
anomaly_type="cost_spike",
agent_id="agt_abc123",
limit=20,
)
Filter by status: open, acknowledged, resolved
Filter by type: cost_spike, reliability_decay, behavioral_drift, security_threat
[
{
"id": "ano_abc123",
"agent_id": "agt_xyz789",
"agent_name": "production-summarizer",
"anomaly_type": "cost_spike",
"severity": "high",
"status": "open",
"description": "Token spend increased 340% vs 7-day average",
"detected_at": "2026-03-17T09:45:00Z",
"details": {
"current_cost_usd": 45.20,
"baseline_cost_usd": 10.30,
"deviation_percent": 338.8
}
}
]
get_anomaly()
Get a single anomaly by ID.
anomaly = client.get_anomaly("ano_abc123")
acknowledge_anomaly()
Mark an anomaly as acknowledged. This indicates a human has reviewed it.
client.acknowledge_anomaly(
"ano_abc123",
note="Expected spike — batch processing job ran today",
)
Optional note explaining the acknowledgment
resolve_anomaly()
Mark an anomaly as resolved.
client.resolve_anomaly(
"ano_abc123",
resolution="Batch job completed. Cost will return to normal tomorrow.",
)
Description of how the anomaly was resolved
get_anomaly_summary()
Get a summary of anomaly counts by type and status.
summary = client.get_anomaly_summary()
{
"total": 12,
"by_status": {
"open": 3,
"acknowledged": 5,
"resolved": 4
},
"by_type": {
"cost_spike": 6,
"reliability_decay": 3,
"behavioral_drift": 2,
"security_threat": 1
}
}
