The warning before the failure
Two lines of code.
That's the entire migration.
Drop-in replacement for Azure Anomaly Detector and AWS Lookout for Equipment. Same API, same JSON schema. Change the endpoint and API key. Done.
Replaces Azure Anomaly Detector
and AWS Lookout for Equipment
Change your endpoint URL. Change your API key. Everything else stays exactly the same. Your existing code, your existing JSON schema, your existing integrations. All unchanged.
Azure API: 100% Wire Compatible
Same JSON format, same endpoints, same auth header. Your Azure SDK code works without modification.
/detect/entire-- batch detection over the full series/detect/last-- streaming detection on the latest point- Identical request and response JSON schema
Ocp-Apim-Subscription-Keyheader supported
AWS Lookout: Synchronous REST Replacement
Lookout used async S3 uploads and scheduled inference. Canary Edge replaces this with a real-time synchronous REST API. Same detection, no waiting.
- POST sensor data, GET anomaly scores in under 50ms
- No S3 uploads, no async polling, no model training wait
- Multivariate detection (2-100 channels) with per-channel scoring
- No AWS lock-in. Works with any cloud, any historian
- endpoint = "https://YOUR.cognitiveservices.azure.com"
- key = "AZURE_SUBSCRIPTION_KEY"
+ endpoint = "https://api.canaryedge.com"
+ key = "CANARY_API_KEY"
# That's it. Everything else stays the same.
# Same JSON body. Same response fields. Same auth header.Azure Field Mapping
Field Mapping
| Azure Field | Canary Field | |
|---|---|---|
series | series | |
series[].timestamp | series[].timestamp | |
series[].value | series[].value | |
granularity | granularity | |
maxAnomalyRatio | maxAnomalyRatio | |
sensitivity | sensitivity | |
customInterval | customInterval | |
period | period | |
isAnomaly | isAnomaly | |
isPositiveAnomaly | isPositiveAnomaly | |
isNegativeAnomaly | isNegativeAnomaly | |
expectedValues | expectedValues | |
upperMargins | upperMargins | |
lowerMargins | lowerMargins |
Encoder
Compress raw time-series into latent representations
Predictor
Forecast expected latent state from context window
Energy Scorer
Compute reconstruction energy as anomaly signal
Regime Classifier
Map energy to operational regime via z-score thresholds
State-of-the-Art AI Engine
Canary Edge uses a purpose-built time-series AI model that learns the normal dynamics of your machines — no labeled anomaly data required. Upload your data and we fine-tune to your equipment for perfect accuracy.
Superior to legacy ML
Outperforms ARIMA, Prophet, Isolation Forest, and every statistical method on standard benchmarks by 15-30%.
Per-machine fine-tuning
Upload your normal operating data. We train a model specific to your equipment in seconds, not hours.
Context-aware detection
Understands temporal dynamics — catches gradual drift, regime shifts, and contextual anomalies that threshold-based tools miss.
Real-time Detection
Sub-50ms inference at the 99th percentile. Canary Edge is optimized for production workloads that demand low-latency anomaly detection.
Batch mode
Submit an entire time series and receive anomaly flags for every point. Ideal for historical analysis and backfilling.
Streaming mode
Send the latest data point and get an instant determination. Designed for live monitoring and alerting pipelines.
Production-grade SLA
Engineered for 99.9% uptime with horizontal scaling and graceful degradation under load.
Inference Latency (p99)
Canary Edge
48ms
Azure Anomaly Detector
220ms
AWS Lookout
350ms
Open Source (PyOD)
480ms
Throughput
12,000
requests/sec (batch)
45,000
requests/sec (streaming)
Sensor Model
High-frequencyVibration, temperature, pressure sensors sampled at sub-second intervals. Captures fast transient anomalies.
Metrics Model
Low-frequencyBusiness metrics, daily aggregates, hourly counters. Optimized for trend shifts and seasonal deviation.
Multi-resolution Models
One size does not fit all time series. Canary Edge ships two model variants optimized for different data characteristics and automatically selects the right one based on your series.
Automatic selection
The API inspects granularity and sample rate to route your data to the optimal model. No configuration needed.
Tuned architectures
Each variant has a purpose-built encoder depth, context window, and feature extraction pipeline.
Unified API
Both models expose the same request/response contract. Swap between them transparently.
Per-machine Fine-tuning
Start with a generic pre-trained model, then fine-tune the predictor head on each individual machine. The system learns what "normal" looks like for your specific equipment.
Zero-shot baseline
The generic model provides accurate detection out of the box. No training period required to start.
Automatic adaptation
As data flows in, the predictor head adapts to each machine's unique patterns and operating modes.
Continual improvement
Detection accuracy improves over time as the fine-tuned model captures more operational context.
Fine-tuning Progression
Generic Model
82%Pre-trained encoder and predictor provide a strong baseline for all machine types.
Initial Fine-tune
91%After 24 hours of data, the predictor head begins adapting to machine-specific patterns.
Mature Model
97%After 7 days, the model captures seasonal patterns, maintenance cycles, and load variations.
HEALTHY
z < 1.0Normal operating conditions. Energy scores within one standard deviation of the running baseline.
ACTIVE
1.0 <= z < 2.0Elevated activity. Mild deviations that may indicate changing load, warm-up, or non-critical drift.
TRANSITION
2.0 <= z < 3.0Warning zone. Significant deviation from normal behavior. Investigate or prepare for intervention.
SHOCK
z >= 3.0Critical anomaly. Extreme energy spike beyond three standard deviations. Immediate attention required.
Regime Classification
Beyond binary anomaly flags, Canary Edge classifies every data point into one of four operational regimes. This gives operators context-aware severity levels instead of just "anomaly or not."
Z-score thresholds
Regimes are determined by the standardized distance of the energy score from the running baseline mean.
Actionable severity
Each regime maps to a clear operational response: monitor, investigate, or act immediately.
Temporal tracking
Track regime transitions over time to identify degradation trends before they become critical failures.
How Canary Edge Compares
A side-by-side comparison of anomaly detection platforms.
| Feature | Canary Edge | Azure Anomaly DetectorAzure | AWS LookoutAWS | Open SourceOSS |
|---|---|---|---|---|
| Azure + AWS Lookout Compatible | ||||
| Self-supervised (no labels) | ||||
| P99 Latency | <50ms | ~220ms | ~350ms | varies |
| Per-machine Fine-tuning | manual | |||
| Regime Detection | ||||
| Streaming + Batch | ||||
| Multi-resolution Models | ||||
| Starting Price | $0 free tier | Retired | $0.05/1K inf. | Self-host |
Ready to migrate?
Switch from Azure Anomaly Detector or AWS Lookout for Equipment in under 90 seconds.