Collected sources and patterns will appear here. Add from search, explore, or the patterns library.
DatasetFile + SchemaMapping -> StandardizedDataset
Map arbitrary tabular dataset columns to standard evaluation schema keys like prompt, response, and context.
Problem it solves
Raw evaluation datasets use divergent column names, making generalized evaluation pipelines difficult to run without schema alignment.
Consumes
Emits
The real projects this mechanism was found in. Attribution is the point — this is how the best teams actually do it.