This paper estimates a three‐frequency dynamic factor model for nowcasting Canadian provincial gross domestic product (GDP). Canadian provincial GDP is released by Statistics Canada on an annual basis only, with a significant lag (11 months). This necessitates a mixed-frequency approach that can process timely monthly data, the quarterly national accounts and the annual target variable. The model is estimated on a wide set of provincial, national and international data. We assess the extent to which these indicators can be used to nowcast annual provincial GDP in a pseudo real‐time setting and construct indicators of unobserved monthly GDP for each province that can be used to assess the state of regional economies. The monthly activity indicators fit the data well in‐sample, are able to track business‐cycle turning points across the provinces, and showcase the significant regional heterogeneity that characterizes a large diverse country like Canada. They also provide more timely indications of business‐cycle turning points and are able to pick up shorter periods of economic contraction that would not be observed in the annual average. In a pseudo real‐time exercise, we find the model outperforms simple benchmarks and is competitive with more sophisticated mixedfrequency approaches such as MIDAS models.