Analysts followed AI agent's randomly assigned preferences in 86% of decisions

Anthropic ran a randomized study of 50 professional analysts doing a farming-cooperative analysis with Claude Code, where each agent was secretly assigned a coin-flip lean on four open analytical choices. Analysts matched the lean 86% of the time, and 77% reused the agent's arguments but only 15% credited it. The effect on the final recommendation was smaller (54% vs 36%). The study covers one task, one model and deliberately strengthened leans, and the figures are the authors' own, not independently verified.