The use of textual data to measure economic uncertainty has gained prominence in empirical macroeconomic research, particularly following Baker et al.'s seminal work in 2016. In this project, I extend the application of Natural Language Processing (NLP) methods to analyze textual data from FOMC (Federal Open Market Committee) minutes and statements. My objective is to create an NLP-based measurement for tracking the Federal Reserve's uncertainty regarding inflation. Using simple macroeconometric models, I estimate how this index drives inflation expectations and the extent of its impact on actual inflation rates. These findings offer valuable insights into the effectiveness of the Federal Reserve's forward guidance in shaping the real economy.