Most Python developers reach for DuckDB because it is fast. This talk explains why it is fast — and what that means for how you should use it. We start at the engine layer: columnar storage, the push-based vectorised execution model, and how DuckDB's query planner differs from row-oriented databases. We then move to the Python integration layer: zero-copy exchange with Arrow and pandas, the relation API versus raw SQL, and how DuckDB manages memory within your process. The second half is benchmarks — DuckDB vs pandas vs PySpark on aggregations, joins, and window functions at 10M, 100M, and 1B rows — with honest commentary on where each tool belongs in a modern data stack. Leave with a mental model, not just a tutorial.