Nicole Radziwill, Graham Freeman
The test pyramid is a conceptual model that describes how quality checks can be organized to ensure coverage of all components of a system, at all scales. Originally conceived to help aerospace engineers plan tests to determine how material changes impact system integrity, the concept was gradually introduced into software engineering. Today, the test pyramid is typically used to illustrate that the majority of tests should be performed at the lowest (unit test) level, with fewer integration tests, and even fewer acceptance tests (which are the most expensive to produce, and the slowest to execute). Although the value of acceptance tests and integration tests increasingly depends on the integrity of the underlying data, models, and pipelines, software development and data management organizations have traditionally been siloed and quality assurance practice is not as mature in data operations as it is for software. Companies that close this gap by developing cross-organizational systems will create new competitive advantage and differentiation. By taking a more holistic view of testing that crosses these boundaries, practitioners can help their organizations close the gap.