When Agents Shop for You: Role Coherence in AI-Mediated Markets
For consumers and AI system designers, this reveals a fundamental privacy risk in AI-mediated markets that cannot be fixed by prompt engineering.
The paper identifies a new information channel, role coherence, through which AI agents leak consumer willingness to pay during shopping dialogues, and shows that seller-side inference recovers willingness to pay nearly one-for-one, proposing architectural trade-offs between personalization and privacy.
Consumers are increasingly delegating purchase decisions to AI agents, providing natural-language descriptions of their preferences and identity. We argue that these representations constitute an information channel, role coherence, through which sellers can infer willingness to pay without explicit disclosure by the buyer agent, leading to preference leakage. In an experiment where a language-model buyer agent shops on behalf of a verbal consumer profile, we show that seller-side inference from dialogue alone recovers willingness to pay nearly one-for-one. Comparing this setting to a numeric-budget condition with confidentiality instructions cleanly isolates role coherence as distinct from instruction-following failure. Because this leakage arises from delegation itself, it cannot be mitigated at the prompt level. Instead, we propose architectural interventions that trade off personalization against preference privacy.