Selector AI Presents at Cloud Field Day 22

Enhanced Observability and Correlation for Hybrid Networks with AIOps from Selector AI

Watch on YouTube
Watch on Vimeo

Selector AI, presented at Cloud Field Day, showing an AIOps solution providing comprehensive visibility and intelligence into the complex networks, cloud infrastructure, and applications of large enterprises.  Unlike existing monitoring tools focusing on single data sources (metrics, logs, events), Selector ingests diverse data types from various sources including existing databases and monitoring tools,  config events, alerts, topology information, and even CSV files. This unified approach allows for advanced event correlation, drastically reducing alert volume and the associated workload on operations teams.

Selector’s natural language interface is a key differentiator, enabling users to query the platform using plain English rather than complex SQL queries.  This, coupled with a digital twin capability for operational insights and “what-if” analysis, provides a significantly more user-friendly and accessible experience. The platform integrates with various communication channels like Slack and Microsoft Teams and ITSM tools, enabling proactive alerting and reactive querying across different teams and workflows, breaking down the typical siloed approach of NOC centres.

Selector’s deployment model offers flexibility, supporting public and private cloud environments, on-premise installations, and even integration directly into existing Google Cloud or AWS instances.  Importantly, their pricing model is not tied to data volume or user count, instead focusing on a predictable cost structure based on monitored devices and use cases. This allows for more straightforward budgeting and encourages the ingestion of larger datasets, which in turn improves the accuracy and effectiveness of Selector’s insights.  While Selector integrates with existing tools, its ultimate aim is to provide a single source of truth, eventually replacing the need for multiple, disparate monitoring systems as customers realize its efficiency and comprehensive capabilities.

Personnel: Deba Mohanty

A Day in the Life of the Enterprise Administrator with Selector AI

Watch on YouTube
Watch on Vimeo

Selector AI’s presentation at Cloud Field Day 22, delivered by VP of Product Sachin Natu, focused on illustrating a typical day for a cloud engineer managing Fortune 500 company environments. Natu highlighted the significant challenges these engineers face, emphasizing the complexity arising from the multitude of technologies, administrative domains, and siloed views across on-premise networks, multiple ISPs, and hybrid cloud deployments. The core problem showcased was the difficulty in troubleshooting even a seemingly simple issue like a malfunctioning chatbot, requiring investigation across numerous interconnected systems and data sources.

The presentation centered around Selector AI’s platform, which aims to address these complexities by providing a Slack-native AI-powered interface. Using a scenario involving a chatbot outage, Natu demonstrated how the platform proactively identifies problems, correlates events across various systems (including network devices, ISPs, and cloud services), and provides actionable recommendations within the Slack workspace itself. The platform doesn’t simply identify issues; it also offers contextual information, such as historical data and user-added notes, to build a clear picture of the situation, allowing for more efficient and informed decision-making.

Crucially, Natu differentiated Selector AI’s approach from generative AI, emphasizing the platform’s reliance on machine learning techniques for accurate data analysis and correlation, rather than generating hypothetical solutions. While leveraging Large Language Models (LLMs) for natural language interaction, the core of the platform uses precise data analysis to ensure accurate representations of the systems being monitored. This approach addresses concerns about the reliability of AI-driven insights in critical infrastructure management and ensures that the recommendations provided are grounded in factual data and historical context. The presentation concluded with a planned deeper dive into the platform’s architecture and data processing methods.

Personnel: Sachin Natu

Customer Use Cases and Product Demonstration with Selector AI

Watch on YouTube
Watch on Vimeo

Selector AI’s presentation at Cloud Field Day 22 showcased real customer use cases demonstrating how its platform aids operators and management teams in making critical cloud-based business decisions. John Heintz, Global Systems Engineering Director, highlighted the platform’s ability to resolve critical issues rapidly, emphasizing its unique position in meeting the daily needs of operators and management. The presentation featured a recorded demo showcasing the platform’s functionality, including the creation of “smart tickets” that automatically summarize events, provide context, and suggest remediation actions. The demo further illustrated how these tickets integrate with collaboration tools like Slack, offering a streamlined workflow for incident management.

A key aspect of the demo involved the platform’s dynamic dashboarding capabilities. These dashboards are contextually driven, automatically generated based on the details of an alert, presenting relevant topology renderings, color-coded KPIs, and drill-down capabilities for deeper investigation. The presenter addressed audience questions regarding the dashboards’ dynamic generation, highlighting the utilization of JSON data from alerts to build visualizations on the fly, while emphasizing the possibility of customer customization. He also explained how the platform’s chat ops functionality allows users to interact with the system using natural language, eliminating the need for complex queries and streamlining the investigation process.

The demo also showcased Selector AI’s capacity to integrate various data sources, including cloud providers’ native monitoring services, and its ability to correlate events across different systems to pinpoint root causes. The presenter highlighted features like correlation graphs and a time-series DVR function, which allow users to visualize the sequence of events leading to an incident. Finally, the discussion addressed the platform’s architecture, emphasizing its scalability built on Kubernetes and the use of techniques like Kafka for efficient data processing, and the flexibility to deploy agents to collect data from various environments. This ability to ingest data from diverse sources, whether existing monitoring tools or directly from the target systems, represents a core strength of the Selector AI platform.

Personnel: John Heintz

A Deep Dive into AIOps with Selector AI

Watch on YouTube
Watch on Vimeo

Selector AI’s presentation at Cloud Field Day 22 offered a technical deep dive into the architecture and functionality of its platform. The core of the platform relies on machine learning (ML) techniques for data ingestion and analysis, ingesting raw data such as metrics, events, and syslogs to understand network behavior without generating content. This ML-driven process focuses on accuracy, utilizing methods like regressions, clustering, and cosine similarities to identify patterns and correlations within the data, avoiding the hallucinations often associated with Large Language Models (LLMs).

The platform’s unique strength is its ability to handle a wide variety of data sources, leveraging a declarative ETL and compiler to easily ingest new data types. This flexibility is showcased by the system’s ability to process data from diverse sources, ranging from legacy network devices and modern cloud services to custom CSV files. The system’s architecture is built on Kubernetes, ensuring horizontal scalability to handle the volume and velocity of data ingested, with a strong focus on creating context through the integration of CMDB data and metadata to give meaning to the raw data. This data integration is a critical component, bringing together disparate data silos to provide a holistic view of network operations.

Generative AI plays a supporting role in Selector AI’s platform, primarily enhancing user experience. It translates natural language queries into the platform’s query language and converts the resulting JSON output back into human-readable English. This use of generative AI is carefully managed to ensure accuracy, acting as a complementary tool to the underlying ML engine and not replacing it. The platform is designed to be flexible, allowing customers to utilize various LLMs and ensuring that the system learns and adapts to the specific details of each customer’s network infrastructure over time. The company emphasizes its commitment to customer support, providing ongoing platform maintenance and support throughout the entire lifecycle of their product implementation.

Personnel: Sachin Natu