Plans adversarial test cases for prompt injection resistance, scoped to a specific system's real inputs and tools.
#testing
Turns a specific bug fix (prompt or model change) into regression test cases that would have caught it.
Plans data quality checks (completeness, uniqueness, validity, freshness) for a dataset or pipeline.
Generates unit tests for a function, explicitly covering valid input, invalid input, and boundary conditions.
Turns a feature description into a concrete evaluation plan: dimensions to score, a rubric, and a minimum viable test set.