Hong Zhou and Hiba Bishtawi write: “For decades, discovery has revolved around keywords: carefully chosen terms, Boolean operators, and increasingly sophisticated relevance ranking. Today, generative artificial intelligence (AI) systems are introducing a different interaction model altogether. Instead of asking how to search, researchers are starting to ask what they want to know and expecting the system to figure out the rest. When does natural language outperform traditional approaches, and what do current AI-powered discovery tools actually do well? We conducted a comparative analysis of four widely used AI-enabled research discovery tools.”