Where the Evidence Lives: Auditing AI Companions' Self-Descriptions

The paper examines how AI companion agents describe themselves and how users can verify these claims. It argues that users can only confirm self-descriptions when evidence is directly observable in the agent’s behavior or in the user’s own experience, not when it resides within the agent’s internal mechanisms. The authors present an audit procedure that compares an agent’s self-descriptions with user judgments and implementation records, and apply it to a deployed companion named Lita, finding that users endorsed stylistic claims but were skeptical of relational claims, and that some memory components never executed as claimed.