bi-bigdata-knowledge

Big-data / distributed-compute reasoning and review layer for BI and data agents in the Seshat BI project. Use when data is too large for single-node pandas and the agent must reason about distributed or larger-than-memory processing — choosing an engine (Spark / Dask / Polars / DuckDB / warehouse), controlling partitioning and shuffle, avoiding skew and fan-out, aggregating at a declared grain at scale, choosing…