Nokia Introduces Agentic AI Framework in Network Services Platform

Nokia said it enhanced its Network Services Platform to add an agentic AI framework aimed at supporting AI operations for IP networks. The change centers on deploying AI agents that can act within defined policies and security boundaries based on a current network view.

Nokia described a need for operators to manage growth in IP network size and complexity, including increased AI traffic, while maintaining operational control. The company said its approach embeds agentic AI capabilities into NSP, which it described as the authoritative controller for IP networks.

Under the framework, Nokia said AI agents are grounded in a real-time, continuously updated view that includes topology, protocol behaviour, configuration state, service relationships, and recent network changes. The agents reason on that network context and operate within operator-defined intent, policies, and access controls, while also supporting communication with external agents via AI-based protocols including Model-context protocol (MCP).

Nokia said the first use case built on the framework is an AI-driven Troubleshooting Agent for identifying root causes faster and reducing operational noise. Nokia also said NSP would support the introduction of multiple AI use cases over time using a shared framework for consistent governance and operational controls, with commercial availability by the end of 2026.

“Appledore has been advocating for operators to focus on the primary importance of quality data and ontological relationships – which are proving far more important than specific AI models for efficient and accurate AI reasoning. Nokia’s NSP embraces this approach with extensive AI-native infrastructure built on trusted data and operating norms, providing a solid and secure foundation for a myriad of AI use cases. Domain expertise is likely the most critical quality in designing effective automation for complex networks,” said Grant Lenahan, Partner and Principal Analyst, Appledore Research. “The industry is moving quickly toward AI-native operations, but trust remains the deciding factor. We are enhancing NSP with AI agents built on an agent framework in a way that respects how networks are actually operated. This will have a major impact on the way operators manage their networks and will enable them to enhance their operations significantly and accelerate their journey toward autonomous networks with focus on solving real operational problems, starting with high-impact use cases like troubleshooting. This is an incremental, pragmatic step toward AI‑native networks,” said Sasa Nijemcevic, Vice President and General Manager, IP Network Automation software unit, Nokia.