Summary
In this chapter, we learned how to create unit tests and implement linting augmentation with AI. We examined security considerations and the return on investment as we progress further with utilizing LLMs to augment our CI/CD pipeline. Specifically, we utilized the Poe SDK in Python to interact with a purpose-built bot for analyzing our use cases. We followed up the lab by complementing unit testing with linting in pull requests using CodeRabbit’s AI service. Finally, we wrapped up by considering multiple-LLM model validation and a voting calculation to help bolster our tests.
In the upcoming chapter, we’ll pivot to a metric-focused view of how to measure the success of the detections implemented using our detection-as-code strategy.
