PersonaCite: VoC-Grounded Interviewable Agentic Synthetic AI Personas for Verifiable User and Design Research

TL;DR

PersonaCite introduces an evidence-grounded AI persona system that retrieves real customer data, provides source attribution, and enhances verifiability for design research, addressing limitations of prompt-based synthetic personas.

Contribution

It presents PersonaCite, a novel retrieval-augmented AI system that makes synthetic personas verifiable and transparent by grounding responses in actual voice-of-customer evidence.

Findings

Industry experts see benefits in verifiability and transparency.

Concerns about evidence sufficiency and response accuracy.

Design tensions around balancing evidence retrieval and conversational flow.

Abstract

LLM-based and agent-based synthetic personas are increasingly used in design and product decision-making, yet prior work shows that prompt-based personas often produce persuasive but unverifiable responses that obscure their evidentiary basis. We present PersonaCite, an agentic system that reframes AI personas as evidence-bounded research instruments through retrieval-augmented interaction. Unlike prior approaches that rely on prompt-based roleplaying, PersonaCite retrieves actual voice-of-customer artifacts during each conversation turn, constrains responses to retrieved evidence, explicitly abstains when evidence is missing, and provides response-level source attribution. Through semi-structured interviews and deployment study with 14 industry experts, we identify preliminary findings on perceived benefits, validity concerns, and design tensions, and propose Persona Provenance Cards as a documentation pattern for responsible AI persona use in human-centered design workflows.