Experiment with Azure Machine LearningRun training scripts and track models with MLflow in Azure Machine LearningPerform hyperparameter tuning with Azure Machine LearningTune hyperparameters in Azure DatabricksUse MLflow in Azure DatabricksUse AutoML in Azure DatabricksTrain a machine learning model in Azure DatabricksManage a machine learning model in productionTrain deep learning models on Azure DatabricksRun pipelines in Azure Machine LearningTrigger Azure Machine Learning jobs with GitHub ActionsDeploy a model with GitHub ActionsPlan and prepare a GenAIOps solutionManage prompts for agents in Microsoft Foundry with GitHubEvaluate and optimize AI agents through structured experimentsAutomate AI evaluations with Microsoft Foundry and GitHub ActionsEvaluate risk and safety metrics for a generative AI appGenerate a synthetic dataset for generative AI evaluationSelect, deploy, and evaluate modelsExplore foundation models in the model catalogExplore language models in Azure DatabricksSet up RAG with Azure DatabricksImplement multi-stage reasoning with LangChainFine-tune a language model with Azure DatabricksOptimize and fine-tune AI agents for productionEvaluate a language model with Azure DatabricksImplement LLMOps in Azure DatabricksMonitor your generative AI applicationAnalyze and debug your generative AI app with tracingText guardrailsImage guardrailsGroundedness detectionPrompt ShieldsSecure Azure OpenAI with content safety controls
Proseware Case Study - Design machine learning solutionFind the best classification model with Azure Machine LearningOptimize model training in Azure Machine LearningPerform hyperparameter tuning with a sweep jobPlan and prepare an MLOps solution with Azure Machine LearningAutomate model training with GitHub ActionsDeploy and monitor a model in Azure Machine LearningDevelop prompt and agent versionsDesign and optimize promptsAutomated evaluation with cloud evaluatorsMonitor and trace your generative AI agentOptimize AI agents with fine-tuning