• Azure developers building AI-enabled applications
• Back-end developers modernizing applications for Azure
• AI application developers working with cloud APIs and data services
• Power Platform, Dynamics 365, or enterprise developers integrating Azure AI services
• Solution architects who need deeper implementation knowledge
• Technical leads supporting AI application modernization

Prerequisites

Working knowledge of:

• Azure fundamentals
• Python, C#, or another modern development language
• REST APIs and SDK-based development
• Basic container concepts
• Basic database concepts
• Application monitoring and troubleshooting conce

 Course Outline:

Module 1: Introduction to Azure AI Cloud Development

Topics

• Understand the AI cloud developer role on Azure
• Review the Azure AI application development lifecycle
• Identify common AI application architecture patterns
• Compare serverless, containerized, and event-driven designs
• Map AI-200 skills to enterprise AI solution delivery

Supporting Statements

• Students learn how Azure supports complete AI application development from design through deployment, monitoring, and troubleshooting.
• The module explains how developers contribute to secure, scalable, back-end AI services that support intelligent applications and workflows.
• This module establishes the foundation for building production-ready AI cloud solutions rather than isolated AI experiments.

Lab

Lab 1: Review an Azure AI Cloud Architecture
Students analyze a reference architecture for an AI-enabled application using Azure compute, messaging, data storage, security, and monitoring services.

Module 2: Develop Containerized AI Solutions on Azure

Topics

• Understand containerization patterns for AI applications
• Build and package application components into containers
• Deploy containerized workloads to Azure
• Configure container app environments
• Evaluate container hosting options for AI workloads

Supporting Statements

• Microsoft Learn states that AI-200T00 covers Azure compute and containerization patterns used to host AI applications.
• Students learn how containers improve portability, scalability, and consistency for AI-enabled services.
• The module connects container strategy to real business scenarios such as AI APIs, background processing, workflow automation, and model-serving integration.

Lab

Lab 2: Containerize and Deploy an AI-Enabled Web API
Students package a sample AI-enabled API into a container and deploy it to Azure.

Module 3: Implement Azure Container Apps for AI Workloads

Topics

• Deploy applications with Azure Container Apps
• Configure revisions and traffic management
• Implement scaling rules for AI workloads
• Use environment variables and secrets
• Monitor container app behavior and performance

Supporting Statements

• Azure Container Apps is positioned by Microsoft as a fully managed serverless container platform for building and deploying apps and agents at scale.
• Students learn how serverless containers reduce infrastructure management while supporting scalable AI application patterns.
• The module emphasizes real-world AI cloud workloads such as API endpoints, background workers, event-driven processing, and microservices.

Lab

Lab 3: Deploy and Scale an Azure Container App
Students deploy a containerized AI service, configure scaling, and review runtime behavior.

Module 4: Build Serverless AI APIs with Azure Functions

Topics

• Create serverless APIs for AI applications
• Compare Azure Functions hosting options
• Configure triggers and bindings
• Connect functions to data and messaging services
• Secure and monitor function-based workloads

Supporting Statements

• Microsoft Learn identifies Azure Functions as part of the AI-200T00 course focus for building serverless APIs.
• Students learn when serverless development is appropriate for lightweight AI APIs, workflow steps, automation tasks, and event-triggered processing.
• The module helps developers design AI components that scale on demand while reducing operational overhead.

Lab

Lab 4: Build a Serverless AI Processing API
Students create an Azure Function that receives input, processes a request, and integrates with another Azure service.

Module 5: Connect and Consume Azure Services

Topics

• Use Azure SDKs and REST APIs
• Authenticate applications to Azure services
• Configure managed identities
• Secure application configuration
• Connect compute, data, and AI services

Supporting Statements

• The related Azure AI Cloud Developer Associate certification expects proficiency with Azure SDKs and third-party SDKs used in Azure.
• Students learn how to connect application components securely without relying on hard-coded credentials.
• The module supports enterprise AI integration scenarios where applications must call Azure AI, data, identity, and messaging services securely.

Lab

Lab 5: Connect an AI Application to Azure Services Securely
Students configure service access using managed identity and application settings.

Module 6: Integrate AI Workflows with Azure Service Bus

Topics

• Understand message-based AI architecture
• Create queues and topics
• Send and receive messages
• Build resilient background processing workflows
• Handle retries, dead-lettering, and processing failures

Supporting Statements

• Microsoft Learn states the course covers message-based architectures such as Azure Service Bus.
• Students learn how messaging supports reliable AI workflows where requests may be long-running, asynchronous, or dependent on external systems.
• The module focuses on practical enterprise patterns such as document processing, order analysis, customer service routing, and AI enrichment pipelines.

Lab

Lab 6: Build a Message-Based AI Processing Pipeline
Students create a Service Bus queue and process AI workload messages using an Azure-hosted application component.

Module 7: Build Event-Driven AI Solutions with Azure Event Grid

Topics

• Understand event-driven cloud architecture
• Publish and subscribe to events
• Connect Azure services with Event Grid
• Trigger serverless and containerized workloads
• Design event-driven AI automation patterns

Supporting Statements

• Microsoft Learn identifies Azure Event Grid as a key integration service in the AI-200T00 course.
• Students learn how event-driven design supports real-time AI automation across cloud services.
• The module shows how AI applications can respond to file uploads, database changes, business events, or operational signals.

Lab

Lab 7: Trigger an AI Workflow from an Event
Students configure an event-driven workflow that starts AI processing when a cloud event occurs.

Module 8: Design AI Data Solutions with Azure Cosmos DB for NoSQL

Topics

• Identify Cosmos DB use cases for AI applications
• Design containers and partitioning strategies
• Query data using NoSQL patterns
• Optimize performance and scalability
• Connect Cosmos DB to AI-enabled application components

Supporting Statements

• Microsoft Learn states the course covers Azure data services that support AI workloads, including designing and querying solutions with Cosmos DB for NoSQL.
• Students learn how to design scalable operational data stores for AI-enabled applications.
• The module connects database design to performance, cost, and application responsiveness.

Lab

Lab 8: Store and Query AI Application Data in Cosmos DB
Students create a Cosmos DB for NoSQL database, load sample application data, and run queries from an application.

Module 9: Use PostgreSQL with pgvector for AI Applications

Topics

• Understand vector data concepts
• Use Azure Database for PostgreSQL with pgvector
• Store embeddings for AI search and retrieval
• Query vector data
• Support retrieval-augmented generation patterns

Supporting Statements

• Microsoft Learn lists Azure Database for PostgreSQL with pgvector as part of the AI-200T00 coverage for AI-supporting data services.
• Students learn how vector-enabled databases support semantic search, similarity matching, and AI-enriched application experiences.
• The module is especially relevant for organizations building custom copilots, knowledge search, AI assistants, and agentic workflows.

Lab

Lab 9: Build a Vector Search Prototype with PostgreSQL and pgvector
Students create a simple vector-enabled data store and perform similarity search against sample content.

Module 10: Implement Azure Managed Redis for Caching, Streaming, and Vector Search

Topics

• Understand caching patterns for AI applications
• Use Redis to improve application responsiveness
• Apply Redis for streaming scenarios
• Explore Redis vector search capabilities
• Design high-performance AI application data access patterns

Supporting Statements

• Microsoft Learn states that Azure Managed Redis is included for caching, streaming, and vector search in AI-200T00.
• Students learn how caching and fast data access improve the user experience of AI-enabled applications.
• The module explains how Redis can support low-latency workloads, session state, repeated prompts, embeddings, and fast retrieval scenarios.

Lab

Lab 10: Improve AI Application Performance with Redis
Students configure Redis caching for a sample AI application and compare response behavior before and after caching.

Module 11: Secure AI Cloud Solutions on Azure

Topics

• Secure application identities
• Protect secrets and configuration
• Apply least-privilege access
• Secure service-to-service communication
• Review secure deployment patterns for AI workloads

Supporting Statements

• The Azure AI Cloud Developer Associate role includes security across the development lifecycle, including design, development, deployment, and monitoring.
• Students learn how to reduce credential exposure and secure AI application components across compute, data, and integration services.
• The module reinforces enterprise security requirements for AI applications that access sensitive organizational data.

Lab

Lab 11: Secure an AI Cloud Application
Students configure identity-based access, secure settings, and validate service permissions.

Module 12: Monitor and Troubleshoot AI Solutions on Azure

Topics

• Configure monitoring for AI applications
• Use Azure Monitor and Application Insights concepts
• Review logs, traces, and metrics
• Troubleshoot failures across distributed services
• Improve reliability and observability

Supporting Statements

• Microsoft Learn states that the course teaches developers how to create, monitor, and troubleshoot AI solutions on Microsoft Azure.
• Students learn how observability helps identify failures across serverless APIs, containers, databases, and messaging workflows.
• The module prepares developers to operate AI solutions in production rather than only deploy them.

Lab

Lab 12: Monitor and Troubleshoot a Distributed AI Application
Students inspect logs, review application telemetry, identify a failure condition, and recommend corrective action.

Module 13: Orchestrate End-to-End AI Workflows on Azure

Topics

• Combine compute, data, messaging, and events
• Build multi-step AI workflows
• Design reliable processing pipelines
• Handle failures and retries
• Align technical workflow design to business processes

Supporting Statements

• Microsoft Learn states that by the end of the course, developers should be able to connect services, orchestrate AI workflows, and build secure, scalable, observable AI-driven applications on Azure.
• Students learn how individual Azure services work together as part of a complete AI application architecture.
• This module connects technical implementation to business scenarios such as customer service automation, intelligent document processing, workflow routing, and operational insights.

Lab

Lab 13: Build an End-to-End AI Cloud Workflow
Students assemble a solution using Azure Functions, Container Apps, Service Bus or Event Grid, and an Azure data service.

Module 14: Capstone Project — Build a Secure Azure AI Cloud Solution

Topics

• Design a complete AI cloud application architecture
• Select Azure compute and data services
• Implement integration and workflow patterns
• Apply security, monitoring, and troubleshooting
• Present a production-readiness review

Supporting Statements

• The capstone reinforces AI-200T00’s core objective: developing secure, scalable, and observable AI-driven applications on Azure.
• Students practice making real implementation decisions across compute, serverless, container, data, messaging, and monitoring services.
• The capstone gives learners a practical portfolio-style project that mirrors enterprise AI modernization work.

Capstone Lab

Capstone: Develop an AI Cloud Solution on Azure
Students design and build a working AI-enabled cloud solution using multiple Azure services, then present the architecture, security model, monitoring approach, and improvement recommendations.