Câu 48: AI-300: Operationalizing Machine Learning and Generative AI Solutions

An organization validates generative AI applications during CI/CD Microsoft Foundry. Evaluation must run automatically and block releases when quality thresholds are NOT met. Manual evaluation is no longer acceptable. Evaluation must use both predefined quality metrics and custom safety checks. You need to implement an automated evaluation workflow that supports both built-in and custom metrics. What should you do?

1. A. Enable application tracing to collect runtime telemetry.
2. B. Review evaluation results manually after deployment.
3. C. Monitor latency metrics during model inference.
4. D. Implement an evaluation step by using GitHub Actions. — đáp án hiện tại