Address
Level 8/25 Restwell Street, Bankstown NSW 2200, Australia
Business Hours
Monday to Friday: 10AM - 6PM
Weekend: CLOSED
AI-300T00: Operationalize machine learning and generative AI solutions
Take machine learning and generative AI from experiment to production. This intermediate, self-paced course teaches MLOps and GenAIOps on Azure, covering pipelines, automated deployment, and agent evaluation and monitoring with Azure Machine Learning, Microsoft Foundry and GitHub Actions. It prepares you for the Microsoft AI-300 exam.
Available in Instructor-Led or Virtual formats.
Duration
4 Days
Modules
13 Modules
Course type
Microsoft
Course Overview
AI-300 equips data scientists, ML engineers, and DevOps professionals with skills to operationalize machine learning and generative AI solutions on Azure. The program covers MLOps and GenAIOps using Azure Machine Learning, Microsoft Foundry, GitHub Actions, Azure CLI, and Bicep. Learners develop capabilities in experimentation, pipelines, hyperparameter tuning, automated deployment, prompt management, agent evaluation, monitoring, tracing, security, and automation to build scalable, reliable AI systems for production environments through structured workflows that enable continuous improvement collaboration and efficient enterprise AI operations.
Before You Begin
- Python and Machine Learning Foundations
- DevOps and Source Control Basics
- Basic Azure and Command-Line Experience
Key outcomes
- Learn to operationalize machine learning solutions using Azure Machine Learning, automation, collaboration, and reliable production workflows.
- Learn to build reusable pipelines, run experiments, and improve model performance through hyperparameter tuning techniques.
- Learn to automate training, testing, deployment, and release processes using GitHub Actions, Azure ML CLI, and cloud resources.
- Learn GenAIOps practices, prompt management, agent workflows, and structured evaluation using Microsoft Foundry and GitHub.
- Learn to track performance, analyze metrics, automate evaluations, and debug AI applications using tracing and observability tools.
Tools you’ll use
Azure Machine Learning
Microsoft Foundry
GitHub & GitHub Actions
Azure CLI
Bicep
MLflow
OpenTelemetry
Skills you’ll gain
- Build and deploy ML solutions using Azure Machine Learning.
- Automate MLOps workflows with GitHub Actions.
- Develop and manage GenAI applications using Microsoft Foundry.
- Evaluate, monitor, and optimize AI models and agents.
- Implement AI automation, tracing, and quality assurance workflows.
What You’ll Learn
13 modules
1Module 1: Get started with machine learning in Azure
1.1 Introduction
1.2 Define the problem
1.3 Get and prepare data
1.4 Train the model
1.5 Use Azure Machine Learning studio
1.6 Integrate a model
1.7 Summary
1.2 Define the problem
1.3 Get and prepare data
1.4 Train the model
1.5 Use Azure Machine Learning studio
1.6 Integrate a model
1.7 Summary
2Module 2: Experiment with Azure Machine Learning
2.1 Introduction
2.2 Preprocess data and configure featurization
2.3 Run an automated machine learning experiment
2.4 Evaluate and compare models
2.5 Configure MLflow for model tracking in notebooks
2.6 Train and track models in notebooks
2.7 Evaluate models with the Responsible AI dashboard
2.8 Exercise – Find the best classification model with Azure Machine Learning
2.9 Summary
2.2 Preprocess data and configure featurization
2.3 Run an automated machine learning experiment
2.4 Evaluate and compare models
2.5 Configure MLflow for model tracking in notebooks
2.6 Train and track models in notebooks
2.7 Evaluate models with the Responsible AI dashboard
2.8 Exercise – Find the best classification model with Azure Machine Learning
2.9 Summary
3Module 3: Run training scripts and track models with MLflow in Azure Machine Learning
3.1 Introduction
3.2 Convert a notebook to a script
3.3 Run a script as a command job
3.4 Use parameters in a command job
3.5 Track metrics with MLflow
3.6 View metrics and evaluate models
3.7 Exercise – Optimize model training in Azure Machine Learning
3.8 Summary
3.2 Convert a notebook to a script
3.3 Run a script as a command job
3.4 Use parameters in a command job
3.5 Track metrics with MLflow
3.6 View metrics and evaluate models
3.7 Exercise – Optimize model training in Azure Machine Learning
3.8 Summary
4Module 4: Perform hyperparameter tuning with Azure Machine Learning
4.1 Introduction
4.2 Define a search space
4.3 Configure a sampling method
4.4 Configure early termination
4.5 Use a sweep job for hyperparameter tuning
4.6 Exercise – Run a sweep job
4.7 Summary
4.2 Define a search space
4.3 Configure a sampling method
4.4 Configure early termination
4.5 Use a sweep job for hyperparameter tuning
4.6 Exercise – Run a sweep job
4.7 Summary
5Module 5: Run pipelines in Azure Machine Learning
5.1 Introduction
5.2 Create components
5.3 Create a pipeline
5.4 Run a pipeline job
5.5 Exercise – Run a pipeline job
5.6 Summary
5.2 Create components
5.3 Create a pipeline
5.4 Run a pipeline job
5.5 Exercise – Run a pipeline job
5.6 Summary
6Module 6: Automate model training with GitHub Actions
6.1 Introduction
6.2 Use source control for machine learning assets
6.3 Apply trunk-based development
6.4 Validate changes with GitHub Actions
6.5 Connect GitHub Actions to Azure Machine Learning securely
6.6 Trigger Azure Machine Learning jobs and pipelines
6.7 Exercise
6.8 Summary
6.2 Use source control for machine learning assets
6.3 Apply trunk-based development
6.4 Validate changes with GitHub Actions
6.5 Connect GitHub Actions to Azure Machine Learning securely
6.6 Trigger Azure Machine Learning jobs and pipelines
6.7 Exercise
6.8 Summary
7Module 7: Deploy and monitor a model in Azure Machine Learning
7.1 Introduction
7.2 Prepare a model for deployment
7.3 Explore the deployment and monitoring architecture
7.4 Control deployments with GitHub environments
7.5 Deploy, promote, and roll back a model with GitHub Actions
7.6 Monitor the deployed model
7.7 Exercise
7.8 Summary
7.2 Prepare a model for deployment
7.3 Explore the deployment and monitoring architecture
7.4 Control deployments with GitHub environments
7.5 Deploy, promote, and roll back a model with GitHub Actions
7.6 Monitor the deployed model
7.7 Exercise
7.8 Summary
8Module 8: Plan and prepare a GenAIOps solution
8.1 Introduction
8.2 Define agent specifications
8.3 Design and optimize your agent
8.4 Explore the GenAIOps lifecycle
8.5 Explore available tools and frameworks to implement GenAIOps
8.6 Exercise – Design agent specifications from team input
8.7 Summary
8.2 Define agent specifications
8.3 Design and optimize your agent
8.4 Explore the GenAIOps lifecycle
8.5 Explore available tools and frameworks to implement GenAIOps
8.6 Exercise – Design agent specifications from team input
8.7 Summary
9Module 9: Manage prompts for agents in Microsoft Foundry with GitHub
9.1 Introduction
9.2 Apply version control to prompts
9.3 Understand Microsoft Foundry agents and prompt versioning
9.4 Organize prompts in GitHub repositories
9.5 Develop safe prompt deployment workflows
9.6 Exercise – Develop prompt and agent versions
9.7 Summary
9.2 Apply version control to prompts
9.3 Understand Microsoft Foundry agents and prompt versioning
9.4 Organize prompts in GitHub repositories
9.5 Develop safe prompt deployment workflows
9.6 Exercise – Develop prompt and agent versions
9.7 Summary
10Module 10: Evaluate and optimize AI agents through structured experiments
10.1 Introduction
10.2 Design evaluation experiments
10.3 Apply Git-based workflows to optimization experiments
10.4 Apply evaluation rubrics for consistent scoring
10.5 Exercise – Evaluate and compare AI agent versions
10.6 Summary
10.2 Design evaluation experiments
10.3 Apply Git-based workflows to optimization experiments
10.4 Apply evaluation rubrics for consistent scoring
10.5 Exercise – Evaluate and compare AI agent versions
10.6 Summary
11Module 11: Automate AI evaluations with Microsoft Foundry and GitHub Actions
11.1 Introduction
11.2 Understand why automated evaluations matter
11.3 Align evaluators with human criteria
11.4 Create evaluation datasets
11.5 Implement batch evaluations with Python
11.6 Integrate evaluations into GitHub Actions
11.7 Exercise – Set up automated evaluations
11.8 Summary
11.2 Understand why automated evaluations matter
11.3 Align evaluators with human criteria
11.4 Create evaluation datasets
11.5 Implement batch evaluations with Python
11.6 Integrate evaluations into GitHub Actions
11.7 Exercise – Set up automated evaluations
11.8 Summary
12Module 12: Monitor your generative AI application
12.1 Introduction
12.2 Why do you need to monitor?
12.3 Understand key metrics to monitor
12.4 Explore how to monitor with Azure
12.5 Integrate monitoring into your app
12.6 Interpret monitoring results
12.7 Exercise – Enable monitoring for a generative AI application
12.8 Summary
12.2 Why do you need to monitor?
12.3 Understand key metrics to monitor
12.4 Explore how to monitor with Azure
12.5 Integrate monitoring into your app
12.6 Interpret monitoring results
12.7 Exercise – Enable monitoring for a generative AI application
12.8 Summary
13Module 13: Analyze and debug your generative AI app with tracing
13.1 Introduction
13.2 Why do you need to use tracing?
13.3 Identify what to trace in generative AI applications
13.4 Implement tracing in generative AI applications
13.5 Debug complex workflows with advanced tracing patterns
13.6 Make informed decisions with trace data analysis
13.7 Exercise – Enable tracing for a generative AI application
13.8 Summary
13.2 Why do you need to use tracing?
13.3 Identify what to trace in generative AI applications
13.4 Implement tracing in generative AI applications
13.5 Debug complex workflows with advanced tracing patterns
13.6 Make informed decisions with trace data analysis
13.7 Exercise – Enable tracing for a generative AI application
13.8 Summary
Certification & Credentials
Certificate track
4 Days
High-Quality Video Lessons
Digital courseware, e-books & audio access
Recorded sessions, accessible on tablet & phone
AI mentor support & module quizzes
Learning Resources
Videos & Engaging Visual Content
Podcasts & Audiobooks
Expert discussions and audio episodes covering key topics
E-Books
Downloadable guides
Module-Wise Quizzes
Interactive quizzes after each module to reinforce learning.
Additional Resources
Study materials, exam prep guides, sandbox labs, and community tutorials.
Frequently asked questions
Who should take the AI-300 course?
AI-300 is designed for data scientists, ML engineers, and DevOps professionals who want to operationalize machine learning and generative AI solutions on Azure.
What are the prerequisites for this course?
Learners should have Python and ML foundations, DevOps and GitHub knowledge, and basic Azure and command-line experience.
Which tools and platforms are covered in the course?
The course covers Azure Machine Learning, Microsoft Foundry, GitHub Actions, Azure CLI, Bicep, MLflow, and OpenTelemetry.
Will I learn how to deploy AI models into production?
Yes, the course teaches automated model deployment, testing, CI/CD workflows, and production-ready MLOps practices.
Does the course cover Generative AI application development?
Yes, learners will develop GenAIOps skills including prompt management, agent evaluation, monitoring, and debugging of AI applications.
| Duration | 4 Days |
|---|---|
| Modules | 13 Modules |
| Course type | Microsoft |
| Category | Microsoft |
| Prerequisites | Python and Machine Learning Foundations, DevOps and Source Control Basics, Basic Azure and Command-Line Experience |
Be the first to review “AI-300T00: Operationalize machine learning and generative AI solutions”
Reviews
There are no reviews yet.