Artificial Intelligence (AI) is making it possible for computers to diagnose some medical diseases more accurately than doctors. Such systems analyze millions of patient records, recognize underlying data patterns, and generalize them for diagnosing previously unseen patients. A key challenge is determining whether a patient's symptoms and history are attributed to a known disease or other factors. Software testers face a similar problem when triaging automation failures. They investigate questions like, Is the failure due to a defect, environmental issue, or nondeterministic test script? Is there current or historical evidence to support one belief over another? Join Tariq King as he describes how test failures and flakiness can be modeled for machine learning (ML) as causal disease-symptom relations. Learn how to extend continuous integration (CI) tools with ML classifiers that, once trained, can predict the source of failures. Tariq shares his experiences using this approach to clean up test failures and flaky tests in CI pipelines. Join Tariq in the fight to find a cure for test flakiness!