Privacy-Preserving Synthetic Data for 'LLM' Workflows R package FakeDataR version 0.2.2 Generate privacy-preserving synthetic datasets that mirror structure, types, factor levels, and missingness; export bundles for 'LLM' workflows (data plus 'JSON' schema and guidance); and build fake data directly from 'SQL' database tables without reading real rows. Methods are related to approaches in Nowok, Raab and Dibben (2016) <doi:10.32614/RJ-2016-019> and the foundation-model overview by Bommasani et al. (2021) <doi:10.48550/arXiv.2108.07258>. Software Imports: dplyr, jsonlite, zip Suggests: readr, testthat (>= 3.0.0), knitr, rmarkdown, DBI, RSQLite, tibble, nycflights13, palmerpenguins, gapminder, arrow, withr Zobaer Ahmed <zunnun09@gmail.com> Comprehensive R Archive Network (CRAN) Zobaer Ahmed [aut, cre] MIT + file LICENSE (https://CRAN.R-project.org/package=FakeDataR/LICENSE) 2025-10-06 application/tgz https://CRAN.R-project.org/package=FakeDataR doi:10.32614/CRAN.package.FakeDataR en-US