CertBlaze

Microsoft Exam Syllabus

AI-300 syllabus, skills measured, and exam topics

The AI-300 exam measures Design and implement an MLOps infrastructure, Implement machine learning model lifecycle and operations, and Design and implement a GenAIOps infrastructure. Use this page to review the current official syllabus, major domains, and source links before exam day.

Open the practice page

Skills measured by domain

Use the weighting table to decide where to spend the most study time.

Domain Weight
Design and implement an MLOps infrastructure 15–20%
Implement machine learning model lifecycle and operations 25–30%
Design and implement a GenAIOps infrastructure 20–25%
Implement generative AI quality assurance and observability 10–15%
Optimize generative AI systems and model performance 10–15%

Detailed outline

Scan each section as a working study checklist instead of one long wall of text.

Design and implement an MLOps infrastructure (15–20%)

  • Create and manage a workspace
  • Create and manage datastores
  • Create and manage compute targets
  • Configure identity and access management for workspaces
  • Create and manage data assets
  • Create and manage environments
  • Create and manage components
  • Share assets across workspaces by using registries
  • Configure GitHub integration with Machine Learning to enable secure access
  • Deploy Machine Learning workspaces and resources by using Bicep and Azure CLI
  • Automate resource provisioning by using GitHub Actions workflows
  • Restrict network access to Machine Learning workspaces

Implement machine learning model lifecycle and operations (25–30%)

  • Configure experiment tracking with MLflow
  • Use automated machine learning to explore optimal models
  • Use notebooks for experimentation and exploration
  • Automate hyperparameter tuning
  • Run model training scripts
  • Manage distributed training for large and deep learning models
  • Implement training pipelines
  • Compare model performance across jobs
  • Package a feature retrieval specification with the model artifact
  • Register an MLflow model
  • Evaluate a model by using responsible AI principles
  • Manage model lifecycle, including archiving models

Design and implement a GenAIOps infrastructure (20–25%)

  • Create and configure Foundry resources and project environments
  • Configure identity and access management with managed identities and role-based access control (RBAC)
  • Implement network security and private networking configurations
  • Deploy infrastructure using Bicep templates and Azure CLI
  • Deploy foundation models by using serverless API endpoints and managed compute options
  • Select appropriate models for specific use cases
  • Implement model versioning and production deployment strategies
  • Configure provisioned throughput units for high-volume workloads
  • Design and develop prompts
  • Create prompt variants and compare performance across different prompts
  • Implement version control for prompts by using Git repositories

Implement generative AI quality assurance and observability (10–15%)

  • Create test datasets and data mapping for comprehensive model evaluation
  • Implement AI quality metrics, including groundedness, relevance, coherence, and fluency
  • Configure risk and safety evaluations for harmful content detection
  • Set up automated evaluation workflows by using built-in and custom evaluation metrics
  • Examine continuous monitoring in Foundry
  • Monitor performance metrics, including latency, throughput, and response times
  • Track and optimize cost metrics, including token consumption and resource usage
  • Configure detailed logging, tracing, and debugging capabilities for production troubleshooting

Optimize generative AI systems and model performance (10–15%)

  • Optimize retrieval performance by tuning similarity thresholds, chunk sizes, and retrieval strategies
  • Select and fine-tune embedding models for domain-specific use cases and accuracy improvements
  • Implement and optimize hybrid search approaches combining semantic and keyword-based retrieval
  • Evaluate and improve RAG system performance by using relevance metrics and A/B testing frameworks
  • Design and implement advanced fine-tuning methods
  • Create and manage synthetic data for fine-tuning
  • Monitor and optimize fine-tuned model performance
  • Manage a fine-tuned model from development through production deployment

Purpose of this document

  • This study guide should help you understand what to expect on the exam and includes a summary of the topics the exam might cover and links to additional resources. The information and materials in this document should help you focus your studies as you prepare for the exam.
  • Useful links: Description
  • How to earn the certification: Some certifications only require passing one exam, while others require passing multiple exams.
  • Certification renewal: Microsoft associate, expert, and specialty certifications expire annually. You can renew by passing a free online assessment on Microsoft Learn.
  • Your Microsoft Learn profile: Connecting your certification profile to Microsoft Learn allows you to schedule and renew exams and share and print certificates.
  • Exam scoring and score reports: A score of 700 or greater is required to pass.
  • Exam sandbox: You can explore the exam environment by visiting our exam sandbox.
  • Request accommodations: If you use assistive devices, require extra time, or need modification to any part of the exam experience, you can request an accommodation.

About the exam

  • Some exams are localized into other languages, and those are updated approximately eight weeks after the English version is updated. If the exam isn't available in your preferred language, you can request an additional 30 minutes to complete the exam.
  • The bullets that follow each of the skills measured are intended to illustrate how we are assessing that skill. Related topics may be covered in the exam.
  • Most questions cover features that are general availability (GA). The exam may contain questions on Preview features if those features are commonly used.

Audience profile

  • As a candidate for this Microsoft Certification, you should have subject matter expertise in setting up infrastructure for machine learning operations (MLOps) and generative AI operations (GenAIOps) solutions on Azure, together referred to as AI operations (AIOps). You need experience training, optimizing, deploying, and maintaining traditional machine learning models by using Azure Machine Learning, in addition to experience deploying, evaluating, monitoring, and optimizing generative AI applications and agents by using Microsoft Foundry.
  • You should have a data science background with experience in Python programming and an entry-level understanding of DevOps practices, including using tools like GitHub Actions and working with command-line interfaces (CLIs).
  • Additionally, you need knowledge and experience in MLOps by using:
  • Machine Learning.
  • Foundry.
  • GitHub Actions.
  • Infrastructure as code (IaC) practices with Bicep and Azure CLI.
  • Your responsibilities for this role include:
  • Designing and implementing MLOps infrastructure.
  • Implementing machine learning model lifecycle and operations.
  • Designing and implementing GenAIOps infrastructure.
  • Implementing generative AI quality assurance and observability.