Large Language Models are powerful research assistants, but do they think like us—and do they share our cognitive biases? This intensive seminar moves beyond hype to empirically test the human-likeness of LLMs within a framework of decision theory and behavioral science. Through a series of ten controlled experiments using a custom GPT application, you will see when AI mirrors, diverges from, or even inverts human judgment. This hands-on experience provides practical, reproducible skills to rigorously test LLM behavior and translate your findings into high-impact research and managerial applications.