Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.canaryedge.com/llms.txt

Use this file to discover all available pages before exploring further.

AWS Lookout for Equipment retires October 7, 2026. Canary Edge handles the same industrial time-series anomaly detection workloads with a simpler API.

​
Key Differences

AWS LookoutCanary Edge
Requires model training before detectionWorks immediately with generic model
S3 bucket for data ingestionDirect API call with JSON payload
Async inference schedulingSynchronous real-time detection
AWS-only deploymentCloud-agnostic API

​
Migration Steps

​
1. Export Your Data

Export your sensor data from S3 into timestamp/value pairs: 
import boto3
import json

s3 = boto3.client("s3")
obj = s3.get_object(Bucket="your-bucket", Key="sensor-data/pump-1.csv")
# Convert to Canary Edge format

​
2. Call the Canary Edge API

import requests

series = [
    {"timestamp": "2026-01-01T00:00:00Z", "value": reading}
    for reading in your_sensor_readings
]

response = requests.post(
    "https://api.canaryedge.com/v1/timeseries/entire/detect",
    headers={
        "Content-Type": "application/json",
        "Ocp-Apim-Subscription-Key": "YOUR_API_KEY",
    },
    json={
        "series": series,
        "granularity": "minutely",
        "sensitivity": 75,
    },
)

​
3. Optional: Fine-Tune for Your Equipment

For equipment-specific accuracy, fine-tune a model with historical normal data: 
requests.post(
    "https://api.canaryedge.com/v1/train",
    headers={
        "Content-Type": "application/json",
        "Ocp-Apim-Subscription-Key": "YOUR_API_KEY",
    },
    json={
        "machine_id": "pump-1",
        "series": normal_operation_data,
    },
)
Future detection calls for pump-1 will automatically use the fine-tuned model.

​
Need Help?

Contact support@canaryedge.com for migration assistance.