Professional Data Mining & ML Protocol: A hypothesis-driven workflow featuring strict leakage-guards, three-layer validation, and statistical rigor for robust AI agent deployment.
Agent
Dispatch as a subagent to execute a specific analysis task. Receives full task specification from the orchestrating agent. Does NOT inherit session context. Examples: Context: An orchestrating agent is running subagent-driven-analysis. user: "Execute Task 3: numeric feature preprocessing" assistant: "Dispatching…
Agent
Use after statistical review has passed to check code quality of analysis code. Reviews for vectorization, reproducibility, clarity, and artifact correctness. Examples: Context: Statistical review has passed for a feature engineering task. user: "Statistical review approved the feature engineering code" assistant…
Agent
Use after an analyst subagent completes a task to verify statistical correctness. Reviews for data leakage, correct metric selection, proper cross-validation, and sound statistical methodology. Examples: Context: A feature engineering task has been completed. user: "Feature engineering for numeric columns is done"…