design a causal study.

Describe a study — treatment, outcome, confounders, and the assumed causal graph. CausalDesigner builds the DAG, enumerates the backdoor paths, and finds a valid minimal adjustment set with real do-calculus (Pearl's back-door criterion via networkx d-separation — it never conditions on a collider or a mediator), then recommends an estimator (difference-in-differences, regression discontinuity, instrumental variables, matching, or covariate-adjusted regression) with its identifying assumptions and the concrete threats to validity. A field tool for the social/economic sciences, where causal-inference best practice is most under-tooled.