Rigor, Trustworthiness, and Credibility in Qualitative Research: The Qualitative Forensic Audit Trail Tool—Artificial Intelligence (QFATT-AI)

Abstract

Qualitative research grapples with persistent questions of trustworthiness and rigor, often lacking the definitive validation metrics of quantitative studies. The audit trail, a systematic documentation of research decisions and methodologies, was proposed in the 1980s as a solution to enhance trustworthiness and credibility. Contemporary implementation has drifted significantly from its original intent, often reduced to a perfunctory checklist or post hoc justification rather than a rigorous analytical tool. This article critiques the current state of audit trails, revealing a conceptual dilution where audit trails serve as mere stamps of approval, devoid of critical engagement or documented discrepancies. In response, this paper introduces the Qualitative Forensic Audit Trail Tool—Artificial Intelligence (QFATT-AI), a novel framework that reimagines the audit trail for the digital age. By integrating generative AI as an external, dialectical partner, the QFATT-AI provides a structured method for challenging researcher bias, improving methodological fidelity, and exploring alternative interpretations through upside-down thinking. We propose the Transparent Reporting of AI Logistics (TRAIL) to improve ethical and clear documentation of AI involvement. This approach moves beyond simple verification to a robust process of falsification and plausibility, offering researchers a practical means to reclaim the audit trail as a dynamic engine for quality and credibility in qualitative inquiry. The QFATT-AI represents an evolution in qualitative research, transforming passive documentation into active, rigorous interrogation.