How each platform builds operational context
Selector collects raw telemetry and operational context together from every vendor, normalizes and enriches it before any model runs, and establishes causation with purpose-built ML before agents act. Amazon CloudWatch is AWS’s native monitoring service for AWS resources and applications, with metrics, logs, alarms, Application Signals, and network monitoring features, plus AI-assisted investigations for AWS environments.
Foundry agents
Rosetta, Loom, TicketMaster, Artist, Herald, Sculptor; MCP and A2A.
Collaboration
Natural language, dashboards, ChatOps, ITSM workflows, query-backed APIs.
Knowledge
Anomaly detection, correlation, causation, forecasting, knowledge graph.
Data Hypervisor
ML schema inference, enrichment, ELT raw preservation, routing.
Collection
Horizontal engines near the source; push and pull; independent scaling.
Sources
Any vendor’s devices, cloud, CMDB, IPAM, ITSM, tools, and files.
AI investigations
AI-assisted operational investigations for AWS resources.
Alarms and insights
Alarms, composite alarms, anomaly detection, Contributor Insights.
Application Signals
Application performance and SLOs for AWS workloads.
Metrics and logs
CloudWatch Metrics and Logs; Logs Insights queries.
Network monitoring
Internet Monitor, Network Monitor, Network Flow Monitor; VPC Flow Logs.
Sources
AWS services, CloudWatch agent, and OpenTelemetry.
Where CloudWatch falls short architecturally:
AWS-scoped: CloudWatch is built for AWS resources. On-premises networks, other clouds, and non-AWS devices sit outside its native scope. Selector correlates every vendor and environment.
Alarm-based correlation: Composite alarms and AI investigations work over AWS signals. Selector determines cause across hybrid network, cloud, and application data.
No device-level network telemetry: CloudWatch does not collect SNMP, gNMI, BMP, or configuration from customer network devices. Selector does.
Use case 1: Observability
Multivendor data collection
CloudWatch gaps
Device-level telemetry from on-premises networks not collected.
Other clouds and on-premises environments outside native scope.
Routing protocol analytics not available.
Selector value
Streaming telemetry, flow, routing, configuration, and context from any vendor in one pipeline.
Routing changes tied to the services they affect, from BMP and IGP state on the customer’s own devices.
Ingestion from files and streams for data with no API.
Use case 1: Observability
Data normalization and enrichment
CloudWatch gaps
Context limited to AWS tags and resources.
Log parsing relies on authored queries.
Network state replay not described.
Selector value
Learned normalization: no parsing templates or rules to maintain.
Raw records retained with original timestamps for replay and re-analysis.
One enrichment layer applies topology, ownership, maintenance, and criticality to every signal.
Use case 1: Observability
AI-powered operational analytics
Both apply machine learning to metrics. CloudWatch is scoped to AWS; Selector correlates AWS with the rest of the estate.
CloudWatch gaps
Analysis scoped to AWS signals.
Hybrid cross-domain correlation not described.
Optical failure prediction not applicable.
Selector value
Per-series models retrained every 30 minutes detect anomalies no threshold would catch.
Automatic correlation across network, cloud, and application signals in one model.
Optical failure prediction and capacity forecasting before impact.
Use case 2: Event intelligence
Event correlation and root cause
Selector example
The Loom agent resolved 214 alerts across six tools to a single fiber cut on one long-haul span, labeled routing reconvergence and cloud failover as consequences, and flagged the secondary path at 78% utilization as the next risk.
Where CloudWatch stops
CloudWatch can show an AWS service degrading. When the cause is a carrier circuit or on-premises device feeding a Direct Connect link, it sits outside CloudWatch’s view.
CloudWatch gaps
Correlation centers on AWS alarms and signals.
A deterministic causation model across hybrid environments is not described.
Network state replay not described.
Selector value
Alert floods collapse into one incident with a named cause, consequences, and next risk.
Telemetry, logs, flow, and configuration correlated with alerts in one model.
Every finding is traceable and reproducible with Network DVR.
Use case 2: Event intelligence
Agents, ITSM, and governed action
Foundry
CloudWatch gaps
AI investigations scoped to AWS.
Customer-defined governed agents from playbooks not described.
Runs only as an AWS service.
Selector value
Sculptor builds governed agents from the team’s own playbooks, acting only on verified findings.
MCP server shares insights and governed actions with other agent platforms.
Every Foundry agent is available now, in every deployment model.
Functionality gained with Selector
1. AWS plus everything else
2. Deterministic diagnosis
3. Detection beyond thresholds
4. Streaming and routing depth
5. Full-fidelity history
6. No templates to maintain
7. Your playbooks as agents
8. Governed action through MCP
9. Custom outcomes with engineers
10. No rip-and-replace
Selector patents driving innovation
Selector vs. Amazon CloudWatch at a glance
The bottom line
Amazon CloudWatch is the native, deeply integrated monitoring service for AWS, with strong metrics, logs, alarms, and AI-assisted investigations for AWS workloads.
Selector is built for hybrid estates. It correlates AWS data with on-premises networks and other clouds in one model, determines cause deterministically, and puts governed agents on top, including agents built from your own playbooks.
30 min
Model retraining cycle
99.9%
Noise reduction
8x
Faster resolution per P1