From Role to Person: Trust Calibration Challenges in Twin Agents
For researchers and designers of agentic AI, this work highlights a novel trust challenge in twin agents that existing calibration frameworks cannot address.
The paper identifies a trust calibration problem specific to twin agents (digital twins of individuals) in professional settings, where three failure modes (schema gap, epistemic gap, model artifact) lack reliable attribution, and existing frameworks fail due to the dissolved human-AI boundary.
Agentic AI has taken on the role of assistant, collaborator, and decision-support tool. We argue the next role on that list is more personal: you. These are digital twins of each individual -- twin agents -- representing their knowledge, perspective, and communicative style to colleagues when they are unavailable. Drawing on early design work in an ongoing project in which agents represent knowledge workers in a professional setting, we identify a trust calibration problem specific to this approach. When a human colleague doubts a twin agent's output, they face three failure modes (a schema gap, an epistemic gap, and a model artifact) with no reliable attribution path between them. Cognitive forcing functions and related frameworks address overreliance effectively in contexts where there is a clear boundary between the AI and the human decision-maker. However, twin agents dissolve that boundary, raising a class of trust calibration challenge these frameworks were not designed to handle. We introduce the concept, distinguish it from digital twins, and outline the research questions this new class of agent demands.