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. Kentik is a network observability platform built around large-scale flow analytics, BGP, synthetic testing, and cloud network visibility, with an AI Advisor for natural-language network investigation.
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.
Kentik
AI Advisor
Natural-language network investigation and summaries.
Insights and alerts
Traffic anomaly detection, DDoS detection, alert policies.
Network analytics
Flow, BGP, cloud, and synthetic analytics.
Kentik data engine
High-scale store for enriched flow and network data.
Collection
Flow ingest, SNMP and streaming telemetry, cloud flow logs, synthetic agents.
Sources
Routers, switches, clouds, internet vantage points, and synthetic agents.
Where Kentik falls short architecturally:
Traffic-first, not incident-first: Kentik’s core strength is traffic and routing analytics; correlation of alerts and events into incidents with a root cause is not its focus. Selector determines cause across domains.
Network-scoped context: Application, log, and CMDB data sit largely outside Kentik. Selector correlates them with network data in one model.
Investigation-led AI: AI Advisor helps engineers query network data; it does not establish deterministic causation. Selector does.
Use case 1: Observability
Multivendor data collection
Kentik gaps
Configuration collection and drift not described.
Log analytics not described.
CMDB and application context limited.
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
Data Hypervisor
Kentik gaps
Enrichment centers on flow dimensions.
Free-form log and CLI data not interpreted.
Network state replay for incidents 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 platforms apply analytics to network data. Kentik’s strength is traffic and routing; Selector correlates traffic with logs, configuration, and application data.
Kentik gaps
Anomaly detection centers on traffic patterns.
Cross-domain correlation with application and log data not described.
Optical failure prediction not described.
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
What Kentik shows
Kentik gaps
Alert-to-incident correlation and causation not core.
Symptom-versus-cause labeling 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
Kentik gaps
AI Advisor investigates; governed agents that act are not described.
Customer-defined governed agents not described.
ITSM lifecycle automation not described.
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
Capabilities a team gets on day one with Selector instead of building and maintaining them in-house.
1. From traffic analytics to root cause
Flow and BGP evidence combined with telemetry, logs, configuration, and context, with a named root cause instead of engineer-driven analysis.
2. Deterministic diagnosis
Root cause comes from deterministic topology and domain models, so the same data yields the same answer.
3. Detection beyond thresholds
Per-series models retrained every 30 minutes find conditions no static threshold or rule would catch.
4. Streaming and routing depth
gNMI streaming telemetry and BMP/OBMP and IGP analytics from the customer’s own devices, plus optical failure prediction.
5. Full-fidelity history
Raw data preserved with original timestamps; Network DVR replays past network state so findings can be verified and re-run.
6. No templates to maintain
Learned normalization infers structure across vendors and formats, replacing parsing rules and custom collection scripts.
7. Your playbooks as agents
Sculptor turns the team’s own runbooks into governed agents with approved tools, triggers, approval points, and audit.
8. Governed action through MCP
Selector’s MCP server exposes insights, recommendations, and actions to other agent platforms under OAuth2 and RBAC.
9. Custom outcomes with engineers
Forward deployed engineers build integrations, data models, views, and agents on the customer’s own data.
10. No rip-and-replace
Selector deploys alongside Kentik and ingests from existing tools and APIs, adding causal root cause and governed agents above them.
Selector patents driving innovation
Selector vs. Kentik at a glance
The bottom line
Kentik is a leading network traffic analytics platform with high-scale flow, BGP, cloud network, and synthetic visibility.
Selector is built for a different starting point. It correlates traffic with telemetry, configuration, logs, and context in one model, determines cause automatically, 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