The Czech National Bank published a thematic article showing how artificial intelligence can systematically process national financial stability reports to produce a European synthesis of cyclical and structural risks. The analysis covers 463 reports from 28 countries between 2015 and 2025, totaling about 35,200 pages. The article traces risks from the period of very low interest rates and rising credit and property prices through the pandemic, inflation and energy shocks, and the subsequent rapid tightening of monetary conditions. It also identifies common patterns and national differences in macroprudential responses, focusing on countercyclical and systemic risk buffers and borrower based measures such as loan to value, debt to income and debt service to income limits.