This paper presents a No-Code Automated Machine Learning (Auto-ML) platform designed specifically for the energy sector, addressing the challenges of integrating ML in diverse and complex data environments. The proposed platform automates key ML pipeline steps, including data preprocessing, feature engineering, model selection, and hyperparameter tuning, while incorporating domain-specific knowledge to handle unique industry requirements such as fluctuating energy demands and regulatory compliance. The modular architecture allows for customization and scalability, making the platform adaptable across various energy sub-sectors like renewable energy, oil and gas, and power distribution. Our findings highlight the platform's potential to democratize advanced analytical capabilities within the energy industry, enabling non-expert users to generate sophisticated data-driven insights. Preliminary results demonstrate significant improvements in data processing efficiency and predictive accuracy. The paper details the platform's architecture, including data lake and entity-relationship diagrams, and describes the design of user interfaces for data ingestion, preprocessing, model training, and deployment. This study contributes to the field by offering a practical solution to the complexities of ML in the energy sector, facilitating a shift towards more adaptive, efficient, and data-informed operations.