Conversational AI is rapidly becoming a primary interface for information seeking and decision making, yet most systems still assume idealized users. In practice, human reasoning is bounded by limited attention, uneven knowledge, and reliance on heuristics that are adaptive but bias-prone. This article outlines a research pathway grounded in bounded rationality, and argues that conversational AI should be designed to work with human heuristics rather than against them. It identifies key directions for detecting cognitive vulnerability, supporting judgment under uncertainty, and evaluating conversational systems beyond factual accuracy, toward decision quality and cognitive robustness.