{"id":"W7116782278","doi":"10.20944/preprints202512.1693.v1","title":"Design and Evaluation of an AI-Based Conversational Agent for Travel Agencies: Enhancing Training, Assistance, and Operational Efficiency","year":2025,"lang":"","type":"preprint","venue":"Preprints.org","topic":"AI in Service Interactions","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Agencia Canaria de Investigación, Innovación y Sociedad de la Información; European Commission; Leukemia and Lymphoma Society of Canada","keywords":"Documentation; Operational efficiency; Focus (optics); Agency (philosophy); Tacit knowledge; Automation; Product (mathematics); Tourism; Interface (matter)","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001776362,0.000608923,0.0003005986,0.0002681807,0.0003930529,0.001215694,0.001305283,0.0009282014,0.003143018],"category_scores_gemma":[0.003219661,0.0002764168,0.0002624705,0.0001319753,0.0004834114,0.001097199,0.0007955904,0.000518667,0.0007804597],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007186336,"about_ca_system_score_gemma":0.001002748,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002530945,"about_ca_topic_score_gemma":0.001774758,"domain_scores_codex":[0.9990922,0.0004163185,0.0000746727,0.0001613286,0.0001761644,0.00007929379],"domain_scores_gemma":[0.9987438,0.0005518012,0.00007561543,0.0001320163,0.0003226192,0.0001741828],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.005496614,0.002941138,0.01141387,0.001649905,0.0002471198,0.001629915,0.009079301,0.09013052,0.4368301,0.00869152,0.008135948,0.423754],"study_design_scores_gemma":[0.0006359165,0.005239119,0.005735022,0.00006785108,0.0003283853,0.0006823448,0.001804716,0.763216,0.1861161,0.001374328,0.03468931,0.0001109604],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6533462,0.0002006013,0.3238176,0.0004120698,0.0001033066,0.002381076,0.0002667936,0.01097707,0.008495323],"genre_scores_gemma":[0.710392,0.00009479903,0.280685,0.0001600433,0.00001471234,0.0006839226,0.0003388563,0.0002838373,0.007346679],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.003143018,"threshold_uncertainty_score":0.01051444,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2403429053978636,"score_gpt":0.4051225027365588,"score_spread":0.1647795973386952,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}