{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007710267,0.0001604781,0.0002057568,0.0003585137,0.00008354906,0.00009771471,0.00113906,0.0003033511,0.0003190417],"category_scores_gemma":[0.001724856,0.0001613051,0.00005485927,0.000685769,0.00006276244,0.0004559941,0.0002932098,0.0004938422,0.00004563279],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003295522,"about_ca_system_score_gemma":0.007608559,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003571528,"about_ca_topic_score_gemma":0.00006355739,"domain_scores_codex":[0.9973031,0.0001464843,0.0005338906,0.0005785998,0.001113896,0.0003240587],"domain_scores_gemma":[0.9987075,0.00007609217,0.00008851153,0.0005985412,0.0001332413,0.0003961419],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000003682343,0.001016246,0.004586976,0.0001175364,0.000008807078,0.000006071123,0.002478576,0.00002744988,0.00001630743,0.07650972,0.01265173,0.9025769],"study_design_scores_gemma":[0.0009817466,0.00003012264,0.05322076,0.001319952,0.000009486337,0.0000273468,0.0005747202,0.8777829,0.00008125876,0.03452787,0.03105827,0.000385578],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2708354,0.001259982,0.5315309,0.1732125,0.01136498,0.001068759,7.505222e-7,0.0002860974,0.01044055],"genre_scores_gemma":[0.9619377,0.00005850432,0.009727487,0.02637868,0.0004529726,0.0003767093,0.00002281923,0.00001059981,0.001034534],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9021913,"threshold_uncertainty_score":0.9980174,"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."}}