Intent-based networking (IBN) enables network operators to define high-level objectives that determine the network’s behavior and functionality without requiring the specification of procedures to achieve them. While the abstraction simplifies the process of expressing the operator’s intent, translating these goals into syntactically accurate and executable configurations remains a challenging task, especially with the growing complexity of the new generation of networks. In this chapter, we introduce a framework utilizing LLMs to automate the generation of Kubernetes YAML configuration files from natural language prompts. The framework enables precise conversion of operator intents into YAML configurations, bridging the gap between human-defined requirements and machine-executable configurations. Fundamentally, this approach uses a Graph Neural Network (GNN)-based ranking algorithm designed to annotate unlabeled YAML files, which, combined with fine-tuning techniques, empowers LLMs to interpret operator goals and produce syntactically and semantically correct YAML configurations. This resulting framework minimizes potential errors while streamlining the configuration generation process. Experimental results demonstrate that the framework achieves high accuracy in terms of relevance ranking (72%) and efficiently generates YAML configurations. These outcomes demonstrate how the system can be utilized to improve operational progress and scale IBN management systems for future networks.