• Nokia NSP adds an agentic AI framework that lets operators deploy AI agents grounded in a real-time, accurate network view — enabling them to reason based on trusted data and take guided, explainable actions within operator-defined policies and security boundaries.
• Nokia AI-driven Troubleshooting Agent accelerates root-cause analysis, reduces operational noise, and turns complex IP issues into guided, explainable workflows.
• Framework supports communication with external agents via new AI-based protocols across operators’ multi-vendor, multi-domain networks, empowering them on their journey toward fully autonomous networks.

Nokia  announced an enhancement to its Network Services Platform, the company’s comprehensive management and automation platform for multi-vendor IP networks, with the introduction of an agentic AI framework designed specifically for IP network operations. The new framework enables network operators to deploy AI agents that can reason over real network context and take guided actions within defined policy and security boundaries.

As IP networks grow in size and complexity with the rise of AI traffic, operators face increasing pressure to improve efficiency and reliability while maintaining full operational control. While AI has the potential to transform network operations, many operators have remained cautious due to concerns around explainability, trust, and risk in production environments. Nokia’s approach with NSP addresses these concerns by embedding agentic AI capabilities directly into the platform that already serves as the authoritative controller for IP networks.

“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.

NSP grounds AI agents in an accurate and continuously updated view of the network, including topology, protocol behaviour, configuration state, service relationships, and recent network changes. This enables AI agents to reason based on network truth, rather than inferred or fragmented data, and to operate within operator-defined intent, policies, and access controls. The NSP agent framework also allows for communication with external agents via AI-based protocols, such as Model-context protocol (MCP), across operators’ multi-vendor, multi-domain networks empowering them on their journey toward fully autonomous networks.

The first use case built on this new framework is an AI-driven Troubleshooting Agent, aimed at helping operators identify root causes faster, reduce operational noise, and resolve complex IP network issues with greater confidence. This marks a significant step in Nokia’s strategy to help operators adopt AI safely, incrementally, and at scale in live networks.

“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.

For network operators, the new agentic framework provides a flexible foundation to introduce multiple AI use cases over time without creating siloed solutions. Operators can start with focused, high-confidence scenarios and gradually expand the role of AI as trust builds, using a shared framework that enforces consistent governance and operational controls.

End-users also benefit from this evolution through faster fault resolution, improved service reliability, and reduced likelihood of prolonged or cascading outages—delivering better experiences without increasing operational risk.

This enhancement to NSP, which will be commercially available by the end of 2026, reinforces Nokia’s commitment to enabling trusted, AI‑native network operations, and to helping operators translate AI innovation into real, measurable operational outcomes.