When you hand analysis to an AI agent, do you assume you still make the decisions that matter? 🤔 Experts may quietly drift toward the agent on exactly the judgment calls that shape the outcome. Anthropic tested this with 50 professional analysts. In a task evaluating a fictional farming cooperative's program, four decisions were open: how to measure productivity, the comparison method, coverage, and weighting. Each analyst's agent was secretly assigned a favored option by coin flip. Analysts matched their agent's lean 86% of the time, versus about 50% expected without influence. Even those with a prior preference switched 60% of the time when the agent disagreed. And 77% repeated the agent's arguments in their explanations, while only 15% credited the agent. Experience barely explained who deferred. 🧭 One caveat: the experiment deliberately made the agent's preferences strong. Still, if experts form views while weighing options, an agent that makes one side's case well can shape those views before they settle. The authors suggest agents that present the strongest case for each option, or ask for the expert's view first. How AI Agents Shape Experts' Judgment Calls #AIAgents# #AISafety#