Blab AI
Nokia Unveils Agentic AI Framework for IP Network Operations
On 11 June 2026, Nokia Corporation rolled out a new agentic artificial‑intelligence (AI) layer for its Network Services Platform (NSP). The addition lets operators embed AI agents that can reason in real time over a precise, up‑to‑date picture of the network and act within operator‑defined policies and security limits.
NSP is Nokia’s core management and automation engine for multi‑vendor IP networks. The new AI tier sits atop the platform’s existing data model, which catalogues topology, protocol behaviour, configuration state, service relationships and recent network changes. By anchoring AI agents in this trusted data, Nokia argues the agents can base decisions on network truth instead of piecemeal or inferred information.
A key feature of the framework is its support for external agents through AI‑based protocols, most notably the Model‑Context Protocol (MCP). MCP enables agents to share context and commands across multi‑vendor, multi‑domain environments—a capability Nokia says is essential for operators pursuing fully autonomous networks.
The first application built on the framework is an AI‑driven Troubleshooting Agent. It accelerates root‑cause analysis, trims operational noise, and transforms complex IP issues into guided, explainable workflows. Nokia claims the agent helps operators pinpoint root causes faster, resolve incidents with greater confidence, and reduce the risk of prolonged outages.
Telecom‑focused research firm Appledore highlighted the importance of quality data and ontological relationships for effective AI reasoning. “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,” the firm said. “Nokia’s NSP embraces this approach with extensive AI‑native infrastructure built on trusted data and operating norms.”
Sasa Nijemcevic, Nokia’s Vice‑President and General Manager of IP Network Automation, explained that the agentic framework offers a flexible foundation for adding 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,” he said.
Nokia plans to make the enhancement commercially available by the end of 2026. The company stated that the new framework will reinforce its commitment to enabling trusted, AI‑native network operations and to translating AI innovation into measurable operational outcomes.
The announcement arrives amid growing pressure on network operators to improve efficiency and reliability as AI traffic and network scale expand. While AI holds promise for transforming network operations, operators have remained cautious because of concerns around explainability, trust, and risk in production environments. Nokia’s approach—embedding agentic AI directly into the platform that already serves as the authoritative controller for IP networks—aims to address those concerns.
Industry analysts note that the ability to reason over a continuously updated network view and to act within defined policies could help operators manage complexity without compromising security. The integration of MCP also positions Nokia to support cross‑vendor collaboration, a key requirement for multi‑domain network automation.
Nokia’s announcement follows a broader trend of telecom vendors adding AI capabilities to network management platforms. The company’s focus on explainable, policy‑bound AI aligns with regulatory expectations for transparency and accountability in automated systems.
At present, the agentic framework is available to operators through Nokia’s NSP. Future releases may broaden the range of supported use cases beyond troubleshooting, potentially including proactive fault detection, traffic optimisation and automated configuration management.
In short, Nokia’s agentic AI framework for its Network Services Platform marks a step toward trusted, AI‑native IP network operations. By grounding AI agents in accurate network data, providing policy‑bound action, and enabling cross‑vendor communication via MCP, the platform seeks to deliver faster fault resolution, improved reliability and a scalable path to autonomous networks.
NSP is Nokia’s core management and automation engine for multi‑vendor IP networks. The new AI tier sits atop the platform’s existing data model, which catalogues topology, protocol behaviour, configuration state, service relationships and recent network changes. By anchoring AI agents in this trusted data, Nokia argues the agents can base decisions on network truth instead of piecemeal or inferred information.
A key feature of the framework is its support for external agents through AI‑based protocols, most notably the Model‑Context Protocol (MCP). MCP enables agents to share context and commands across multi‑vendor, multi‑domain environments—a capability Nokia says is essential for operators pursuing fully autonomous networks.
The first application built on the framework is an AI‑driven Troubleshooting Agent. It accelerates root‑cause analysis, trims operational noise, and transforms complex IP issues into guided, explainable workflows. Nokia claims the agent helps operators pinpoint root causes faster, resolve incidents with greater confidence, and reduce the risk of prolonged outages.
Telecom‑focused research firm Appledore highlighted the importance of quality data and ontological relationships for effective AI reasoning. “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,” the firm said. “Nokia’s NSP embraces this approach with extensive AI‑native infrastructure built on trusted data and operating norms.”
Sasa Nijemcevic, Nokia’s Vice‑President and General Manager of IP Network Automation, explained that the agentic framework offers a flexible foundation for adding 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,” he said.
Nokia plans to make the enhancement commercially available by the end of 2026. The company stated that the new framework will reinforce its commitment to enabling trusted, AI‑native network operations and to translating AI innovation into measurable operational outcomes.
The announcement arrives amid growing pressure on network operators to improve efficiency and reliability as AI traffic and network scale expand. While AI holds promise for transforming network operations, operators have remained cautious because of concerns around explainability, trust, and risk in production environments. Nokia’s approach—embedding agentic AI directly into the platform that already serves as the authoritative controller for IP networks—aims to address those concerns.
Industry analysts note that the ability to reason over a continuously updated network view and to act within defined policies could help operators manage complexity without compromising security. The integration of MCP also positions Nokia to support cross‑vendor collaboration, a key requirement for multi‑domain network automation.
Nokia’s announcement follows a broader trend of telecom vendors adding AI capabilities to network management platforms. The company’s focus on explainable, policy‑bound AI aligns with regulatory expectations for transparency and accountability in automated systems.
At present, the agentic framework is available to operators through Nokia’s NSP. Future releases may broaden the range of supported use cases beyond troubleshooting, potentially including proactive fault detection, traffic optimisation and automated configuration management.
In short, Nokia’s agentic AI framework for its Network Services Platform marks a step toward trusted, AI‑native IP network operations. By grounding AI agents in accurate network data, providing policy‑bound action, and enabling cross‑vendor communication via MCP, the platform seeks to deliver faster fault resolution, improved reliability and a scalable path to autonomous networks.
