{"id":{"repo_id":"calpoly","oai_identifier":"oai:digitalcommons.calpoly.edu:theses-4938"},"canonical_url":"https://search.ndltd.org/etd/calpoly/oai:digitalcommons.calpoly.edu:theses-4938","repository":{"repo_id":"calpoly","name":"Cal Poly","base_url":"https://digitalcommons.calpoly.edu/do/oai/"},"display":{"title":"AI Interview Helper: A Tool for Assisting Search and Rescue Long-Profile Interviews","abstract":"In Search and Rescue (SAR) operations, time pressure and limited interviewer experience can lead to missed opportunities when interviewing a missing person’s friends and family. This thesis presents a real-time, end-to-end system that provides context-aware follow-up question suggestions as interviews unfold. Leveraging large language models (LLMs) and agentic design patterns, the system is intended to support interviewers by helping them identify relevant follow-up questions and pursue potentially overlooked lines of inquiry. The system was evaluated through three mock interviews with two SAR interviewer participants across two events. Given the limited sample size, the results provide early insights into the feasibility of AI-assisted interviews. Qualitative feedback indicated that many generated questions were relevant and, in some cases, surfaced lines of inquiry they had not previously considered. Quantitative results suggest strong usability, with System Usability Scale (SUS) scores improving from 77.5 to 95 across iterations and participants reporting a high likelihood of recommending the system (9/10 to 10/10). Overall, this work provides early evidence of the technical feasibility and perceived value of real-time LLM-assisted interviewing tools in mock SAR contexts. The findings suggest that such tools may support more thorough questioning, motivating future work to evaluate their effects on clue discovery, interview completeness, and missed information.","abstract_html":"In Search and Rescue (SAR) operations, time pressure and limited interviewer experience can lead to missed opportunities when interviewing a missing person’s friends and family. This thesis presents a real-time, end-to-end system that provides context-aware follow-up question suggestions as interviews unfold. Leveraging large language models (LLMs) and agentic design patterns, the system is intended to support interviewers by helping them identify relevant follow-up questions and pursue potentially overlooked lines of inquiry. The system was evaluated through three mock interviews with two SAR interviewer participants across two events. Given the limited sample size, the results provide early insights into the feasibility of AI-assisted interviews. Qualitative feedback indicated that many generated questions were relevant and, in some cases, surfaced lines of inquiry they had not previously considered. Quantitative results suggest strong usability, with System Usability Scale (SUS) scores improving from 77.5 to 95 across iterations and participants reporting a high likelihood of recommending the system (9/10 to 10/10). Overall, this work provides early evidence of the technical feasibility and perceived value of real-time LLM-assisted interviewing tools in mock SAR contexts. The findings suggest that such tools may support more thorough questioning, motivating future work to evaluate their effects on clue discovery, interview completeness, and missed information.","abstract_has_math":false,"creators":["Starink, Dylan P"],"institution":null,"degree_name":"MS in Computer Science","degree_level":null,"degree_discipline":"Computer Science","degree_department":null,"school":null,"contributors":["Franz Kurfess","Computer Science","College of Engineering"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":null,"date_issued":"","date_published":null,"updated_at":"2026-11-19T07:12:51Z","subjects":["Artificial Intelligence and Robotics","Graphics and Human Computer Interfaces","Software Engineering"],"languages":[],"rights":[],"rights_urls":[],"identifier_entries":[],"person_identifier_entries":[]},"links":{"outbound_url":"https://digitalcommons.calpoly.edu/theses/3269","outbound_label":"Repository record","outbound_source":"dc:identifier","record_url":"https://digitalcommons.calpoly.edu/theses/3269","record_label":"Repository record","record_kind":"record","record_source":"dc:identifier","download_url":null,"download_label":null,"download_source":null,"access_status":null,"embargo_until":null,"access_note":null},"source_record":{"url":"https://digitalcommons.calpoly.edu/do/oai/?verb=GetRecord&metadataPrefix=oai_etdms&identifier=oai%3Adigitalcommons.calpoly.edu%3Atheses-4938","prefix":"oai_etdms"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Franz Kurfess","Computer Science","College of Engineering"]},{"key":"dc:creator","label":"Author","values":["Starink, Dylan P"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.available","label":"Dc Date Available","values":["2026-06-03T07:00:00Z"]},{"key":"dc:date.created","label":"Dc Date Created","values":["2026-06-01T07:00:00Z"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Computer Science"]},{"key":"thesis:degree_name","label":"Degree Name","values":["MS in Computer Science"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Artificial Intelligence and Robotics","Graphics and Human Computer Interfaces","Software Engineering"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://digitalcommons.calpoly.edu/theses/3269"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["In Search and Rescue (SAR) operations, time pressure and limited interviewer experience can lead to missed opportunities when interviewing a missing person’s friends and family. This thesis presents a real-time, end-to-end system that provides context-aware follow-up question suggestions as interviews unfold. Leveraging large language models (LLMs) and agentic design patterns, the system is intended to support interviewers by helping them identify relevant follow-up questions and pursue potentially overlooked lines of inquiry. The system was evaluated through three mock interviews with two SAR interviewer participants across two events. Given the limited sample size, the results provide early insights into the feasibility of AI-assisted interviews. Qualitative feedback indicated that many generated questions were relevant and, in some cases, surfaced lines of inquiry they had not previously considered. Quantitative results suggest strong usability, with System Usability Scale (SUS) scores improving from 77.5 to 95 across iterations and participants reporting a high likelihood of recommending the system (9/10 to 10/10). Overall, this work provides early evidence of the technical feasibility and perceived value of real-time LLM-assisted interviewing tools in mock SAR contexts. The findings suggest that such tools may support more thorough questioning, motivating future work to evaluate their effects on clue discovery, interview completeness, and missed information."]},{"key":"dc:title","label":"Title","values":["AI Interview Helper: A Tool for Assisting Search and Rescue Long-Profile Interviews"]}]}],"canonical_facts":{"dc:contributor":["Franz Kurfess","Computer Science","College of Engineering"],"dc:creator":["Starink, Dylan P"],"dc:date.available":["2026-06-03T07:00:00Z"],"dc:date.created":["2026-06-01T07:00:00Z"],"dc:description.abstract":["In Search and Rescue (SAR) operations, time pressure and limited interviewer experience can lead to missed opportunities when interviewing a missing person’s friends and family. This thesis presents a real-time, end-to-end system that provides context-aware follow-up question suggestions as interviews unfold. Leveraging large language models (LLMs) and agentic design patterns, the system is intended to support interviewers by helping them identify relevant follow-up questions and pursue potentially overlooked lines of inquiry. The system was evaluated through three mock interviews with two SAR interviewer participants across two events. Given the limited sample size, the results provide early insights into the feasibility of AI-assisted interviews. Qualitative feedback indicated that many generated questions were relevant and, in some cases, surfaced lines of inquiry they had not previously considered. Quantitative results suggest strong usability, with System Usability Scale (SUS) scores improving from 77.5 to 95 across iterations and participants reporting a high likelihood of recommending the system (9/10 to 10/10). Overall, this work provides early evidence of the technical feasibility and perceived value of real-time LLM-assisted interviewing tools in mock SAR contexts. The findings suggest that such tools may support more thorough questioning, motivating future work to evaluate their effects on clue discovery, interview completeness, and missed information."],"dc:identifier":["https://digitalcommons.calpoly.edu/theses/3269"],"dc:subject":["Artificial Intelligence and Robotics","Graphics and Human Computer Interfaces","Software Engineering"],"dc:title":["AI Interview Helper: A Tool for Assisting Search and Rescue Long-Profile Interviews"],"thesis:degree_discipline":["Computer Science"],"thesis:degree_name":["MS in Computer Science"]},"updated_at":"2026-11-19T07:12:51Z"}