NETSCOUT Enhances AI-Driven Network Operations with TM Forum’s NeuroNOC Catalyst
NETSCOUT Systems recently took part in TM Forum’s NeuroNOC Catalyst project showcased at DTW Ignite 2025. This event brought together the highest number of Communication Service Providers and countries in DTW Ignite’s history. TM Forum is a global alliance that sets standards and builds frameworks for telecom and technology companies to develop new operating models and software platforms.
What is the NeuroNOC Catalyst Project?
The NeuroNOC Catalyst focused on how AI agents, closed-loop automation, and quality network data can create self-healing network operations in telecom environments. This initiative involved collaboration with key players such as Amazon Web Services, Accenture, Symphonica, and Sand Technologies. Leading carriers like BT Group, Telecom Argentina, Omantel, Turknet, Axian Telecom, and Safaricom supported the project.
The goal was to show how AI and automation accelerate fault detection and resolution in live networks, reducing downtime and improving service reliability.
NETSCOUT’s Role and Technology
NETSCOUT contributed its Omnis AI Insights Solution, which includes the Omnis AI Sensor and Omnis AI Streamer. These tools provide high-fidelity telemetry for 5G Standalone Radio Access Network (SA RAN) and Packet Core networks, essential for AI-powered operations.
- Omnis AI Sensor: Uses deep packet inspection (DPI) to deliver end-to-end network visibility.
- Omnis AI Streamer: Offers analytics and filtering at the data source via an open API-driven dataset.
These components supply accurate, real-time data that AI models need to analyze network health effectively.
Real-World Impact in Simulated Scenarios
In simulations of service-impact events, network operations center (NOC) engineers used the solution to quickly identify subscriber registration problems. A curated large language model (LLM) helped pinpoint root causes, allowing for remediation with minimal manual work.
The key finding was the critical importance of high-quality curated data. AI models depend heavily on reliable data to deliver meaningful results. Poor data quality leads to ineffective AI outcomes, while well-curated data unlocks better performance in automated network operations.
Operational Benefits and Cost Savings
- Up to an 80% reduction in manual troubleshooting efforts
- Potential 50% decrease in operational costs for service providers
- Reduced data usage and tokenization by AI models, such as AWS Bedrock, by up to 80%
These improvements indicate significant efficiency gains and cost reductions enabled by AI-driven automation powered by precise network data.
Insights from NETSCOUT Leadership
Richard Fulwiler, Senior Director of Product Management at NETSCOUT, emphasized the value of accurate, real-time curated data. He noted that without comprehensive packet collection, correlating issues across multiple data streams and verifying automated fixes is nearly impossible. While fully autonomous networks are still emerging, this project shows how AI agents armed with quality data can speed up and improve network issue resolution.
For operations professionals looking to strengthen AI and automation skills in network management, exploring targeted AI training can provide practical knowledge to work effectively with these emerging technologies. Resources like Complete AI Training offer courses that focus on AI applications relevant to operations roles.
Your membership also unlocks:
