Nokia announced an agentic AI framework embedded in its Network Services Platform (NSP), the company’s management and automation platform for multi-vendor IP networks. The framework enables network operators to deploy AI agents that reason over real-time network context and take guided actions within operator-defined policy and security boundaries, according to a GlobeNewsWire press release published June 11.
Grounded in Network Truth
The core design principle is grounding. NSP feeds AI agents a continuously updated view of the network: topology, protocol behavior, configuration state, service relationships, and recent changes. Agents reason against authoritative network data rather than inferred or fragmented inputs, and operate within operator-defined intent, policies, and access controls.
“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,” said Grant Lenahan, Partner and Principal Analyst at Appledore Research, in the announcement. “Nokia’s NSP embraces this approach with extensive AI-native infrastructure built on trusted data and operating norms.”
MCP for Multi-Vendor Agent Communication
The framework supports agent-to-agent communication via Model-context protocol (MCP) across multi-vendor, multi-domain networks. That interoperability layer matters for operators running heterogeneous infrastructure from multiple equipment vendors who need agents to coordinate across domain boundaries without requiring a single-vendor stack.
First Use Case: Troubleshooting Agent
Nokia is shipping an AI-driven troubleshooting agent as the first application built on the framework. The agent accelerates root-cause analysis, reduces operational noise, and converts complex IP network issues into guided, explainable workflows. The company positions this as an incremental, pragmatic step toward autonomous network operations rather than a full-autonomy deployment.
“We are enhancing NSP with AI agents built on an agent framework in a way that respects how networks are actually operated,” said Sasa Nijemcevic, Vice President and General Manager of Nokia’s IP Network Automation software unit, in the announcement.
The Telco Agent Pattern
Nokia’s approach reflects a pattern emerging across enterprise agent deployments: rather than giving agents broad autonomy, organizations are constraining them within trust boundaries defined by domain-specific data and operator policies. The same principle applies whether the domain is a telco network, a financial trading floor, or a hospital system. Commercial availability is slated for the end of 2026.