{"id":"W4414760587","doi":"10.2196/76661","title":"Beyond Chatbots: Moving Toward Multistep Modular AI Agents in Medical Education","year":2025,"lang":"en","type":"article","venue":"JMIR Medical Education","topic":"Topic Modeling","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Chatbot; Workflow; Modular design; Task (project management); Pipeline (software); Quality (philosophy); Task analysis","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"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":[0.007792844,0.0009452799,0.0003754809,0.0007704201,0.001513168,0.004038406,0.00231964,0.002102881,0.004777006],"category_scores_gemma":[0.01333595,0.0006083014,0.0007807732,0.0004581131,0.00352299,0.005614989,0.007295954,0.002167274,0.001569483],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001484942,"about_ca_system_score_gemma":0.003014178,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002685246,"about_ca_topic_score_gemma":0.003286938,"domain_scores_codex":[0.9955368,0.002877353,0.0001907287,0.000567667,0.0005209189,0.0003065995],"domain_scores_gemma":[0.9894695,0.00571655,0.0009298587,0.001958796,0.0007533723,0.001171872],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0007212404,0.000981548,0.01932093,0.001431966,0.0002319221,0.0008696427,0.02675143,0.1332109,0.04120319,0.2903622,0.01106504,0.4738501],"study_design_scores_gemma":[0.0001652477,0.0009409402,0.003753171,0.000838357,0.0001679598,0.0005528501,0.004825318,0.5647172,0.01740227,0.2692597,0.1372033,0.0001738045],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04582273,0.0005129649,0.939182,0.003692104,0.00009597462,0.0002483066,0.00003418425,0.001920172,0.008491625],"genre_scores_gemma":[0.3956374,0.0003230925,0.5985363,0.0007556986,0.00006252132,0.000341811,0.00008539964,0.0002061639,0.004051737],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007792844,"threshold_uncertainty_score":0.04121298,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01581890272558477,"score_gpt":0.3551135080620776,"score_spread":0.3392946053364929,"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."}}