Sets up a binary classification (propensity scoring) model on Treasure Data for any yes/no outcome — lead scoring, churn, conversion, campaign response, upsell, renewal: a workflow that builds the project's feature table, trains the AI Signals classifier (XGBoost or CatBoost with tuning, threshold selection and SHAP) and writes scores for Parent Segment attributes, then builds the project's classifier agent and dashboard. Use it to start, set up, configure, change, re-run or resume a propensity project and to build or rebuild its agent. Trigger on: set up a propensity model, start a propensity project, predict which customers will churn, score leads by likelihood to convert, predict campaign response, build a churn model, build a lead scoring model, classifier setup, classification workflow, configure the classifier, rebuild the classifier agent, resume classifier setup, classifier runbook. Once the project's classifier agent is installed, questions about model performance, drivers and scores go to it.