Top-rated American telco saves millions in opex with Softility's AI-driven NOI solution for SRE

Significant

MTTD Improvement

Significant

MTTR Reduction

Millions

Saved in Opex

Real-time

Event Correlation & Insights

3-Layer

Distributed Architecture

Scalable

Dual Object-Server Design

blog-featured-image

A top-rated CSP in North America saw daily alert volume grow exponentially alongside its infrastructure, running on legacy, event-driven Netcool systems that couldn't keep pace. Softility replaced the legacy platform with a modern Netcool Operational Insights (NOI)-based event and network management solution, introducing scope-based event grouping and correlation to significantly reduce MTTD and MTTR while cutting operational costs by millions.

Challenge

  • Infrastructure grew exponentially, and daily alert volume grew with it straining a legacy, event-driven (not incident-driven) monitoring environment.

  • The exponential surge in events degraded the telco's ability to monitor and report incidents accurately, driving MTTD and MTTR metrics in the wrong direction.

  • Legacy Netcool products and versions lacked the grouping and correlation capabilities needed to manage event volume at the business's current scale.

Solution

Softility ran workshops, interviews, and detailed analysis sessions to map a roadmap from a legacy, event-driven process to an intelligent, insights-based one. We migrated the telco from its legacy Netcool solution to a new NOI-based platform, introducing scope-based auto-grouping of alarms to manage high event volumes and improve correlation and event quality. The architecture was distributed across three functional layers: Collection, Aggregation, and Presentation, with dual object servers implemented to ensure the platform scales alongside the business’s growing infrastructure.

Benefits:

  • Reduced MTTD and MTTR, with millions of dollars saved through improved operational efficiency.

  • Smarter data ingestion from networks, apps, infrastructure, and multi-hybrid-cloud, on-prem instances, replacing manual, fragmented event monitoring.

  • Proactive, real-time detection and response, replacing reactive, ticket-heavy firefighting with automated triage validating, diagnosing, and ticketing issues before they escalate.


About Softility's

Telecom Solutions

Softility has spent two decades embedded inside telecom NOCs, keeping networks running when failure was never an option: from real-time service assurance during the world’s most-watched live broadcasts, to AI-driven monitoring that cut NOC OpEx by 60% for a top-5 North American carrier. Network-scale intelligence, SLA-grade reliability, and agentic-led solutions engineered to run at the true speed of your infrastructure, not the speed of a quarterly roadmap review.

About Softility's


Autonomous Operations

Manual firefighting doesn’t scale Softility’s Autonomous Operations unify Service Reliability, Network Operations, DataOps, and ITOps with AI-native intelligence, cutting alert noise, shrinking MTTR, and shifting teams from reactive triage to proactive prevention before problems ever reach a customer. The result: Enterprises running Softility’s autonomous solutions have cut NOC OpEx by 60% and MTTR by 55%, freeing skilled engineers for work that actually moves the business forward, not another 2 am page.
  • Capabilities
  • About
  • Resources
  • Careers
  • Contact