Developed automatic tracing for Groq API calls within the harupy/mlflow repository, focusing on enhancing end-to-end observability for Groq-powered workloads. The implementation logs inputs, outputs, and metadata for synchronous Groq interactions, providing a dedicated tracing example to guide usage. Leveraging Python for both API integration and testing, the work aligns with MLflow’s existing tracing framework to improve debuggability and reproducibility. This foundational feature supports future cross-service tracing and governance, addressing the needs of LLMOps and MLOps workflows. The approach emphasizes maintainability and extensibility, setting the stage for broader instrumentation across MLflow integrations without introducing unnecessary complexity.