The AI Interviewer: Mastering Quality, Rigor, and Deployment in Mixed-Methods Evaluation
Conference | Online
About the Event
This event bridges theory and field practice to explore the lifecycle of AI-mediated interviewing. We first present a framework of eight measures to assess AI interview quality and methodological risks. Next, we host a hands-on lab to co-design and deploy a live AI mixed-methods agent. Participants analyze real-time results to see how tools solve bottlenecks while safeguarding evaluative integrity and trust. Join and master the craft of AI-enhanced evidence generation.
Sessões
Webinar
|
Online
June 2, 2026
15:00 PM - 15:45 PM
Artificial intelligence is rapidly entering evaluation practice, yet there is little guidance on how to judge the quality of AI-mediated interviews. This session presents a theory-grounded framework for assessing AI interview performance using eight operational measures derived from evaluation and qualitative research theory. Drawing on an empirical comparison of six LLM-based interviewers across simulated evaluation scenarios, the presentation highlights capability boundaries, methodological risks, and practical safeguards for evaluators considering AI-mediated data collection.
Speakers
| Nome | Título | Biography |
|---|---|---|
| Ali Safarnejad | Ali Safarnejad (PhD) is a Multi-Country Evaluation Specialist with UNICEF covering East Asia and the Pacific. He leads evaluations across humanitarian and development contexts and has a strong interest in improving the efficiency and quality of evaluative evidence through thoughtful use of technology and AI. |
Moderators
| Nome | Título | Biography |
|---|---|---|
Workshop de Capacitação
|
Online
June 3, 2026
15:00 PM - 16:00 PM
Participants will learn how to design and deploy an AI-powered interview agent for mixed-methods data collection in evaluation. Using insights from successful field pilots in humanitarian and development sector evaluations, this hands-on session will guide participants to jointly develop an interview guide, define the agent’s parameters, and deploy a live AI-facilitated survey. Participants will take the survey themselves and review real-time results, reflecting on methodological implications, ethical considerations, data quality, and practical applications.
Speakers
| Nome | Título | Biography |
|---|---|---|
| Ali Safarnejad | Evaluation Specialist | Ali Safarnejad (PhD) is a Multi-Country Evaluation Specialist with UNICEF covering East Asia and the Pacific. He leads evaluations across humanitarian and development contexts and has a strong interest in improving the efficiency and quality of evaluative evidence through thoughtful use of technology and AI. |
Moderators
| Nome | Título | Biography |
|---|---|---|
Resumo
The framework for assessing the quality of ai-mediated interviewing was presented, including results of experiments done on 6 large language models deployed as AI interviewers, and the findings and implications of those experiments for evaluation practitioners considering using AI-mediated interviewing among their data collection tools.
The follow-up workshop demonstrated a live ai interviewer, co-designed in the course of the session with the participants, and deployed for the participants to become the interviewees. The results were shared in realtime, demonstrating one of the advantages of this tool. The recommended uses and limitations of the ai-interviewer were discussed, and future direction for improvements were outlined.
Full writeup of the framework shared for further reading and feedback.
A practical workshop applying the framework measures to conduct ai-mediated interviewing.
Open call for collaboration on projects to pilot the AI-powered interviewer, as demonstrated during the workshop.