The latest Selector release includes:<\/p>\n\n\n\n
- \n
- Selector Copilot with GenAI:<\/strong> GenAI combined with Selector Copilot provides instant access to more meaningful incident summaries, assists with troubleshooting, and enables automated remediation. Copilot helps democratize access to your operational telemetry, helping your team access insights quickly.<\/li>\n\n\n\n
- Monitoring and observability: <\/strong>Collect and analyze telemetry from the network to your applications and everything in between. Empower your operations leaders to address tool sprawl and slash monitoring costs. Improve business outcomes with service-level objectives (SLOs) and service-level agreements (SLAs).<\/li>\n\n\n\n
- Root cause analysis: <\/strong>Identify the root cause of an incident through an innovative causal approach, fast-tracking incident investigation and remediation. Additionally, an integrated feedback loop solicits user input, helping to improve correlations and produce more actionable notifications.<\/li>\n\n\n\n
- Digital twin:<\/strong> With Selector, build and leverage digital representations of the network and IT infrastructure. Visualize traffic flows during routing changes and ensure a seamless client experience with improved capacity planning.<\/li>\n<\/ul>\n\n\n\n
Also, in this release, <\/strong>watch for <\/strong>Selector in the Google Cloud Marketplace in Q2. It will enable frictionless software procurement, simplified vendor management, streamlined pricing, and help burn down cloud commits.<\/p>\n\n\n\n
Now, let’s dig deeper into each of these highlights.<\/p>\n\n\n\n
Selector Copilot with GenAI<\/strong><\/h2>\n\n\n\n
Offered as part of the Selector platform, Selector Copilot combines conversational AI with a natural\/human language query mechanism. It enables your teams to use retrieval-augmented generation (RAG) to enrich and enhance responses with external data sources. <\/p>\n\n\n\n
Let’s examine an Enterprise Wi-Fi Network use case to help you understand Selector Copilot’s powerful capabilities.<\/p>\n\n\n\n
Use case: Enterprise Wi-Fi network <\/h3>\n\n\n\n
In this use case, the operator uses Selector Copilot to understand the status of a Wi-Fi network for an enterprise, such as a hospital, hotel chain, retail store, or bank. The operator starts with the prompt:<\/p>\n\n\n\n
Why is the user experience in a Wi-Fi zone red?<\/code><\/p>\n\n\n\nThey can then prompt answers to more specific questions:<\/p>\n\n\n\n
- \n
- Is the signal-to-noise ratio (SNR) or signal strength indicator (RSSI) not within the permissible limits?<\/li>\n\n\n\n
- Has the Dynamic Host Configuration Protocol (DHCP) Request, DNS Query, or Radius Authentication failed?<\/li>\n\n\n\n
- Why did it fail?<\/li>\n<\/ul>\n\n\n\n
Figure 1 shows this natural language query. Although not shown in this figure, Copilot also includes possible remediations.<\/p>\n\n\n\n
![\"\"](\"https:\/\/www.selector.ai\/wp-content\/uploads\/2024\/03\/image3-1024x752.png\")
Figure 1: Query in natural language on a Slack channel<\/em><\/figcaption><\/figure>\n\n\n\n Monitoring and Observability<\/strong><\/h2>\n\n\n\n
With this release, Selector can not only act on top of existing tools, but can directly collect configuration, metric, event, and log telemetry with its native monitoring capabilities.<\/p>\n\n\n\n
Selector supports over 500 integrations across networks, infrastructures, clouds, and applications. It also integrates seamlessly with legacy monitoring and observability solutions to provide comprehensive insights into the overall IT environment. <\/p>\n\n\n\n
Once the data is collected, Selector leverages machine learning to detect and identify anomalies. It then suppresses the duplicate and non-actionable events and points towards the root cause of an incident, helping the team reduce mean time to detect (MTTD) and mean time to resolve (MTTR).<\/p>\n\n\n\n
Root Cause Analysis<\/strong><\/h2>\n\n\n\n
Causal machine learning helps customers identify related issues and events across multiple data sets to find the underlying root cause of an incident.<\/p>\n\n\n\n
![\"\"](\"https:\/\/www.selector.ai\/wp-content\/uploads\/2024\/03\/image1-1024x557.png\")
Figure 2: Root cause analysis in Selector<\/figcaption><\/figure>\n\n\n\n The process follows this flow:<\/p>\n\n\n\n
- \n
- Machine learning<\/strong> is applied to metrics and logs brought in by Selector’s ingest layer, surfacing anomalies. Additional event data is also analyzed.<\/li>\n\n\n\n
- Metadata<\/strong> from inventory systems, the configuration management database (CMDB), and other sources enrich the resulting anomaly and event data, enabling robust correlations.<\/li>\n\n\n\n
- Recommender models<\/strong> leverage temporal and contextual correlation, linking anomalies for otherwise unrelated events. <\/li>\n\n\n\n
- Association models<\/strong> further analyze anomalies and events, identifying the precipitating event that led to an incident and pointing operators toward the root cause. <\/li>\n<\/ol>\n\n\n\n
Digital Twin<\/strong><\/h2>\n\n\n\n
Create a digital twin of your network and IT infrastructure from the Selector platform. The digital twin feature provides visualization that enables the clients to: <\/p>\n\n\n\n
- Metadata<\/strong> from inventory systems, the configuration management database (CMDB), and other sources enrich the resulting anomaly and event data, enabling robust correlations.<\/li>\n\n\n\n
- Machine learning<\/strong> is applied to metrics and logs brought in by Selector’s ingest layer, surfacing anomalies. Additional event data is also analyzed.<\/li>\n\n\n\n
- Monitoring and observability: <\/strong>Collect and analyze telemetry from the network to your applications and everything in between. Empower your operations leaders to address tool sprawl and slash monitoring costs. Improve business outcomes with service-level objectives (SLOs) and service-level agreements (SLAs).<\/li>\n\n\n\n
![\"\"](\"https:\/\/www.selector.ai\/wp-content\/uploads\/2024\/03\/image2.png\")