bauplan-data-pipelines
Creates bauplan data pipeline projects with SQL and Python models. Use when starting a new pipeline, defining DAG transformations, writing models, or setting up bauplan project structure from scratch.
explore-data
Explores data in a Bauplan lakehouse safely using the Bauplan Python SDK. Use to inspect namespaces, tables, schemas, samples, and profiling queries; and to export larger result sets to files. Read-only exploration only; no writes or pipeline runs.
quality-gated-updates
Ingest data from S3 into Bauplan safely using branch isolation and quality checks before publishing. Use when loading new data from S3, importing parquet/csv/jsonl files, or when the user needs to safely load data with validation before merging to main.
root-cause-analysis-and-fix
“Inspect a failed Bauplan pipeline run on a dev branch, reconstruct the frozen data state, collect evidence, propose a minimal code fix using Git, and rerun deterministically where possible.”