Description

This Master Prompt establishes a rigorous methodological framework for demonstrating, evaluating, validating and improving artifacts developed through Design Science Research. It examines the relationships among artifact objectives, design requirements, evaluation criteria, research evidence, stakeholder expectations, operational performance and scientific claims concerning artifact effectiveness. Particular emphasis is placed on distinguishing artifact demonstration from evaluation, verification from validation, technical performance from practical usefulness, and laboratory-based assessment from evaluation under authentic operational conditions. The framework incorporates formative and summative evaluation, ex ante and ex post assessment, artificial and naturalistic evaluation, experimental and quasi-experimental research designs, case studies, field studies, expert evaluation, focus group assessment, usability testing, simulation-based evaluation, benchmarking, comparative analysis and mixed-method validation. Researchers are guided in establishing evaluation objectives, selecting appropriate evaluation methods, defining performance indicators, designing evaluation protocols, determining suitable participant samples, identifying baseline solutions and developing reliable measurement instruments. The Master Prompt addresses quantitative performance metrics, qualitative user feedback, usability dimensions, task completion rates, efficiency, accuracy, effectiveness, reliability, robustness, scalability, acceptance, stakeholder satisfaction and contextual suitability. It also incorporates statistical hypothesis testing, effect size estimation, confidence intervals, sensitivity analysis, uncertainty assessment, measurement reliability, validity evaluation and comparative performance interpretation where appropriate. Researchers are guided in developing evaluation matrices, experimental design diagrams, validation frameworks, performance graphs, statistical tables, usability assessment charts and iterative refinement models. Particular attention is given to interpreting evaluation findings, identifying artifact limitations, documenting design improvements, distinguishing observed outcomes from unsupported causal claims, and determining whether evaluation evidence adequately supports the artifact's intended practical and scientific contributions.