{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00807031,0.0006102844,0.0007406368,0.000523768,0.0006537459,0.0002198483,0.001153629,0.0004100407,0.0005576024],"category_scores_gemma":[0.001075367,0.0007240479,0.0001994831,0.0004308173,0.0003813652,0.0009363969,0.0008069584,0.0006087795,0.00001515253],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007150519,"about_ca_system_score_gemma":0.00634021,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009782951,"about_ca_topic_score_gemma":0.00007812526,"domain_scores_codex":[0.992983,0.001107105,0.001582455,0.002271009,0.001546684,0.0005097365],"domain_scores_gemma":[0.9928736,0.001644059,0.0009630594,0.00130287,0.002985539,0.0002308373],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0006914847,0.001544403,0.01384034,0.002391737,0.0008507975,0.000004968794,0.09340192,0.7587744,0.08624881,0.01578601,0.00005498212,0.02641013],"study_design_scores_gemma":[0.001593772,0.0001543567,0.04825477,0.000667178,0.0003307082,0.000009224362,0.001877997,0.8832719,0.06022007,0.002975117,0.0001175422,0.0005274071],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3373567,0.0001183074,0.6575745,0.0006910603,0.0009496399,0.002642964,0.00008973353,0.00004232757,0.0005346959],"genre_scores_gemma":[0.9215925,0.00003829429,0.07617453,0.0006344544,0.0001071752,0.001083291,0.0001002185,0.00002410655,0.0002453977],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5842358,"threshold_uncertainty_score":0.9995211,"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."}}