We build the first global quarterly narrative database of discretionary government spending actions by applying a fixed GPT–4.1 prompt to Economist Intelligence Unit (EIU) Country Reports. The resulting unbalanced panel covers 62 countries from 1952–2023 and identifies exogenous spending shocks. We validate the measure by replicating expert narrative coding in Romer and Romer (2019), showing that the actions predict subsequent movements in measured government spending, and documenting close