The practice note outlines six approaches to integrating artificial intelligence (AI) and machine learning (ML) into program evaluation, enhancing traditional methods with data-driven insights and improved efficiency. These approaches aim to address the growing need for evaluators to analyze complex datasets accurately while reducing manual effort. They include identifying patterns in data to uncover trends and outliers, using predictive models for forecasting outcomes, pinpointing areas for improvement by analyzing performance, simplifying data interpretation through visualizations, automating data analysis for efficiency, and leveraging dashboards for real-time monitoring and decision-making. The note highlights that while it does not offer guidance for evaluators with limited technical expertise, it provides a framework for integrating AI into evaluation practices. Successful implementation requires understanding stakeholder needs, fostering client engagement, ensuring tool usability, and maintaining effective communication. While AI can enhance evaluation quality and innovation, ethical considerations and biases in AI algorithms must be carefully addressed. These AI-powered techniques can enable more robust, evidence-based decision-making, supporting positive social impact.