A developer has logged a LangChain agent in MLflow using the Databricks Agent Framework's code-based approach, calling mlflow.langchain.log_model(lc_model='/path/to/agent.py', ...). What step must occur next before this agent can be served by a Databricks Model Serving endpoint?
Answer & explanation
Correct answer: C
WHY C is correct: Per the Databricks Agent Framework documentation, after logging the agent, it must be registered to Unity Catalog using mlflow.set_registry_uri('databricks-uc') followed by mlflow.register_model(model_uri=logged_agent_info.model_uri, name='catalog.schema.model_name'). Registration packages the agent as a Unity Catalog model, which is required before deployment to a Model Serving endpoint.
WHY NOT A: mlflow.end_run() closes the active MLflow experiment run but does not register or deploy the model. A logged model that is not registered cannot be deployed to Model Serving.
WHY NOT B: MLflow handles artifact storage automatically in its configured artifact store. Manual cloud storage upload is neither required nor part of the Agent Framework deployment workflow.
WHY NOT D: Code-based logging captures the code file path to execute at serving time. The artifact is the code path reference, not a time-limited generated artifact. Re-running the notebook is not part of the deployment process.