Development of cell reprogramming methods is hindered by low efficiency and the challenge of analyzing rare cells that have yet unknown phenotypes. While cells in a typical biosample can be identified using unbiased single-cell transcriptomics, annotation itself relies on known gene expression signatures. Cells that begin to reprogram within a larger population remain indiscernible using this approach. Work in this area illuminates the unknowns related to our understanding of cell identity and heterogeneity. I will discuss our recent work, including direct cell reprogramming to human hematopoietic stem cells, future directions, and key barriers to discovery in the field.