Microsoft Azure AI Cloud Developer Associate (AI-200) Training

Learning objective: Understand the AI-200 exam, the developer role it measures, and set up your development environment for building AI back ends on Azure.

• The AI-200 exam and the Azure AI Cloud Developer Associate certification
• What changed from AZ-204
• Azure SDKs for Python and third-party SDKs used in Azure
• Resource groups, subscriptions and the Azure CLI
• Architecture of an AI application back end on Azure
• Set up Python, the Azure CLI and the Azure SDKs

Learning objective: Learn to build, store, version and manage container images in Azure Container Registry (ACR).

• Container images and registries
• Building, tagging and versioning images in ACR
• Building and running images with ACR Tasks
• Registry access and authentication
• Build an image with ACR Tasks and push it to a registry

Learning objective: Deploy containers to Azure App Service and configure them safely.

• Deploying container images to App Service
• Supplying environment variables and secrets to containers
• Deployment slots and configuration
• Deploy a containerized API to App Service with app settings and secrets

Learning objective: Deploy applications to Azure Container Apps and scale them on events.

• Container Apps environments and configuration
• Revisions and revision management
• Event-driven scaling with Kubernetes Event-driven Autoscaling (KEDA)
• Deploy an app to Container Apps and scale it from a queue with KEDA

Learning objective: Deploy, monitor and troubleshoot applications on Azure Kubernetes Service.

• Deploying applications to AKS with manifest files
• Services, deployments and configuration in AKS
• Monitoring and troubleshooting AKS and Container Apps with logs, events and end-to-end connectivity checks
• Deploy a multi-container app to AKS and troubleshoot a failing pod

Learning objective: Use Azure Cosmos DB for NoSQL as the data layer of AI applications.

• Connecting with the SDK and running queries
• Optimizing query performance and Request Unit (RU) consumption with indexing policies
• Choosing consistency levels
• Implementing a change feed processor for new or updated items
• Query a Cosmos DB container from Python and tune its indexing policy

Learning objective: Store embeddings and run vector similarity search for semantic retrieval.

• Embeddings and vector similarity
• Storing and retrieving embeddings in Cosmos DB
• Vector indexing and similarity search
• Semantic retrieval for AI applications
• Build semantic search over a product catalogue with Cosmos DB vector search

Learning objective: Use Azure Database for PostgreSQL and pgvector for vector workloads and RAG.

• Connecting and querying with SDKs
• Modelling schemas, tables and data types
• Indexing strategies, query latency and pgvector compute overhead
• Configuring compute, memory and storage for vector workloads
• Vector similarity search and retrieval-augmented generation (RAG) with metadata filters
• Connection optimization for throughput and latency
• Implement a RAG retrieval step with pgvector and metadata filters

Learning objective: Use Azure Managed Redis to make AI solutions faster.

• Caching data and responses
• Expiration and cache invalidation
• Vector indexing and similarity search in Redis
• Add a Redis cache and a vector index to an AI API

Learning objective: Process back-end work reliably with messaging and eventing services.

• Azure Service Bus queues, topics and subscriptions
• Dead-letter queue handling
• Event-driven workflows with Azure Event Grid
• Event Grid filters, custom events and retries
• Process documents through a Service Bus queue and route events with Event Grid

Learning objective: Build serverless APIs and background processing with Azure Functions.

• Building serverless APIs
• Triggers and bindings
• Configuring and deploying function apps
• Create an HTTP-triggered function and a queue-triggered function in Python

Learning objective: Protect secrets and configuration, and observe your solution in production.

• Securing secrets in Azure Key Vault, including rotation and retrieval
• Storing app settings in Azure App Configuration
• Distributed tracing with OpenTelemetry SDKs
• Analyzing logs and metrics with KQL queries
• AI-200 exam tips and mock test review
• Trace a request across services with OpenTelemetry and query it with KQL