Build production AI applications on Azure with containers, vector databases, event-driven messaging, and OpenTelemetry observability. 5-day official course aligned to Exam AI-200.

👥 1329 Enrolled ⏱️ 5 Days 💼 Intermediate Level ⭐ 4.9 ( 194 ) Reviews

500+Courses

10+ YrsExperience

95K+Global Learners

Live Online (Public Batch)

Instructor-led group class, fixed schedule

USD 2595

Private Group

Train your whole team, on your dates

Custom Quote

For Teams

Proceed to Buy Request Info

📄 Download Course PDF

100% Satisfaction Guarantee · Guaranteed to Run · Secure Payment

Course Overview

Behind every AI application that actually works in production sits a lot of unglamorous engineering. Something has to host the containers, queue the inference requests, store the embeddings, cache the hot paths, hold the secrets, and tell you what broke at 3am. That backend is what this course teaches.

AI-200T00 is Microsoft's five-day course for developers building AI-driven applications on Azure, and it is the training path for the new Azure AI Cloud Developer Associate certification that replaces the retiring Azure Developer Associate route.

The course starts with hosting. You will store and manage images in Azure Container Registry, deploy containers to App Service, then move into Azure Container Apps with revisions, health probes, and event-driven autoscaling through KEDA, and on to Azure Kubernetes Service with deployment manifests, ConfigMaps, secrets, and persistent storage.

The middle third is the data layer that AI workloads depend on, and it is unusually thorough. Three separate modules cover Cosmos DB for NoSQL, Azure Database for PostgreSQL with pgvector, and Azure Managed Redis, each taken from basic operations through vector search to index tuning and cost optimization. You will build a RAG document store, a semantic search application, an agent tool backend, and Redis-based vector storage, learning where each platform earns its place.

The final third handles integration and operations. Azure Service Bus for queuing AI operations, Event Grid for event-driven workflows, Azure Functions for serverless backends including building an MCP server, Key Vault and App Configuration for secrets and settings, then OpenTelemetry instrumentation and KQL queries so you can see what your application is doing once real traffic hits it.

Mode of Training

🏫 Classroom 💻 Live Online 🧪 Blended 👨‍👩‍👧‍👦 Private Group

Upcoming Schedules

Start Date	Time	Duration	Mode	Price
Sep 14, 2026	9:00 am - 5:00 pm	5 Days	online	$2595	GTR
Sep 28, 2026	9:00 am - 5:00 pm	5 Days	online	$2595	GTR
Oct 05, 2026	9:00 am - 5:00 pm	5 Days	online	$2595	GTR
Oct 26, 2026	9:00 am - 5:00 pm	5 Days	online	$2595	GTR
Nov 02, 2026	9:00 am - 5:00 pm	5 Days	online	$2595	GTR

+ View more schedules

What you will learn

Implement containerized and serverless AI applications on Azure
Deploy and manage applications using Azure Container Apps and Azure Kubernetes Service
Build AI data solutions with Cosmos DB, PostgreSQL, and Redis
Implement vector search and retrieval patterns for RAG pipelines
Integrate services using event-driven and message-based architectures
Secure applications using Azure Key Vault and configuration management
Monitor, troubleshoot, and optimize applications with Azure Monitor and OpenTelemetry

Who Should Attend This Course?

Cloud developers building AI-powered applications on Azure
Azure developers moving from the AZ-204 path to the new AI-focused certification
Software and backend engineers responsible for the infrastructure behind AI workloads
Developers who need to build RAG systems, vector search, or agent backends in production

Prerequisites

Required:

Programming experience with Python
A basic understanding of cloud computing concepts
Familiarity with Microsoft Azure fundamentals

Recommended:

Experience with backend or API development
Familiarity with Docker and container concepts
Basic knowledge of Kubernetes and AKS
An understanding of SQL and NoSQL databases
Familiarity with event-driven architecture using Service Bus and Event Grid
Basic understanding of AI and ML concepts such as embeddings and vector search
Experience with the Azure CLI or other command-line tools

You do not need machine learning experience. This is an application and data engineering course, not a data science one. What it assumes is that you can write Python and understand how a backend fits together.

📞 Talk to a Learning Advisor

Exam and Certification

This course prepares you for Exam AI-200: Developing AI Cloud Solutions on Azure, leading to the Microsoft Certified: Azure AI Cloud Developer Associate credential.

This certification replaces the retiring Azure Developer Associate (AZ-204) as Microsoft's associate-level credential for Azure developers, reflecting the shift toward AI-integrated application development. If you were working toward AZ-204, AI-200 is the current path.

The exam is booked and paid for separately from the course.

📘 AI-200T00: Develop AI Cloud Solutions on Microsoft Azure Outline

Azure Container Registry. Registries, repositories, and artifacts. Build and run images with ACR Tasks, then tag and version them. Exercise: build and manage a container image with ACR Tasks.

Containers on Azure App Service. Configure container runtime behaviour and application settings, then observe and troubleshoot containerized apps. Exercise: deploy a container to Azure App Service.

Deployment. Container Apps environments, deploying with the Azure CLI and YAML, runtime settings through environment variables and secrets, image pull authentication for private registries, and verifying deployments through logs and status. Exercise: deploy a containerized backend API to Container Apps.

Management. Update images and manage revisions safely, handle the app lifecycle, monitor logs, configure health probes, and optimize container resources. Exercise: diagnose and fix a failing deployment.

Scaling. Configure scale rules, implement event-driven scaling with KEDA, apply KEDA scalers for custom workloads, choose compute resources for performance and cost, and select revision modes. Exercise: configure autoscaling using KEDA triggers.

Deployment. Create Kubernetes deployment manifests, expose applications, and deploy to AKS. Exercise: deploy an AI inference API to Azure Kubernetes Service.

Configuration. Define ConfigMaps for application settings, implement secrets for sensitive data, and attach persistent storage. Exercise: configure apps on Azure Kubernetes Service.

Monitoring and troubleshooting. Monitor application logs and metrics, troubleshoot pods and services, and verify service connectivity and endpoints. Exercise: troubleshoot apps on Azure Kubernetes Service.

Queries. Explore Cosmos DB for NoSQL, implement the SDK, and query data. Exercise: build a RAG document store on Azure Cosmos DB for NoSQL.

Vector search. Store and retrieve embeddings, execute vector similarity queries for semantic search, combine similarity results with metadata filtering, and use the change feed to trigger embedding refresh. Exercise: build a semantic search application.

Performance. Understand indexes, configure range and composite indexes, tune vector indexes for embedding workloads, reduce RU costs through strategic indexing, and choose consistency levels. Exercise: optimize query performance with vector indexes.

Fundamentals. Explore Azure Database for PostgreSQL, connect to it, create and manage schemas, query data, and integrate SDKs and applications. Exercise: build an agent tool backend on Azure Database for PostgreSQL.

Vector search with pgvector. Store and query embeddings, perform fast similarity search, manage index lifecycle and embedding updates, and implement retrieval patterns for RAG pipelines. Exercise: implement vector search on Azure Database for PostgreSQL.

Optimization. Tune PostgreSQL for pgvector, choose and configure vector indexes, optimize data layout, scale for high-volume workloads, and optimize connections. Exercise: optimize vector search performance.

Data operations. Explore Azure Managed Redis, work with client libraries and development practices, and implement data operations. Exercise: perform data operations in Azure Managed Redis.

Event messaging. Publish and subscribe with Redis pub/sub, implement task queues with Redis Streams, and choose between broadcast and coordinated distribution. Exercise: publish and subscribe to events.

Vector storage. Index and query vector data, choose vector types and indexing strategies, and optimize Redis data structures for vector storage. Exercise: implement semantic search in Azure Managed Redis.

Azure Service Bus. Messaging concepts in AI architectures, choosing between queues and topics with subscriptions, structuring messages for AI workloads, and processing messages reliably. Exercise: process messages with Azure Service Bus.

Azure Event Grid. Event-driven patterns for AI solutions, event schemas and properties, delivery and retry policies, and publishing custom events from AI applications. Exercise: publish and receive events with Azure Event Grid.

Azure Functions. Hosting and scaling for AI workloads, setting up local development, creating triggers and bindings for AI integration patterns, managing secrets and configuration, and configuring identity and access. Exercise: create an MCP server with Azure Functions.

Azure Key Vault. Store and organize secrets, keys, and certificates, retrieve them using SDK client libraries, handle versioning and rotation, and implement caching strategies to reduce Key Vault calls. Exercise: manage secrets with Azure Key Vault.

Azure App Configuration. Connect from application code, organize settings with labels and feature flags, reference Key Vault secrets, and decide what belongs in App Configuration versus Key Vault. Exercise: retrieve settings and secrets from Azure App Configuration.

OpenTelemetry. Its role in observability, adding the SDK to an application, configuring spans and traces, exporting telemetry to Azure Monitor, and debugging distributed flows with trace data. Exercise: instrument an app with the OpenTelemetry SDK.

Telemetry analysis. Write basic KQL queries, explore logs for errors and performance, build dashboards, create workbooks for interactive analysis, and set alerts for failures and anomalies. Exercise: query logs with KQL.

❓ Frequently Asked Questions

Microsoft is retiring the AZ-204 exam and the Azure Developer Associate certification, with AI-200 as the replacement. Much of the developer core carries over, including compute, Functions, Cosmos DB, and messaging. What is new is the AI layer: vector-enabled databases, embedding workloads, RAG retrieval patterns, and the observability that AI applications need. If your study materials are AZ-204-era, plan on updating them.

No. This is a cloud application development course. You need Python and backend development experience, plus Azure basics. The course teaches you to build the infrastructure, APIs, and data layers that AI services run on, not to train models. If model development is your goal, look at Microsoft's machine learning track instead.

Because choosing the wrong data platform is one of the most expensive mistakes in an AI application. Cosmos DB, PostgreSQL with pgvector, and Redis all support vector search, and they suit different workloads. The course takes each from basic operations through vector search to index tuning and cost optimization, so you can make that choice on evidence rather than habit.

Model Context Protocol is the emerging standard for connecting AI models to external tools and data. In Module 7 you build an MCP server using Azure Functions, which is a genuinely current skill and one of the more forward-looking parts of the syllabus.

Most of it. Nearly every topic ends with an exercise, covering container builds, Container Apps deployment and autoscaling, AKS troubleshooting, RAG document stores, semantic search across three data platforms, Service Bus and Event Grid integration, Key Vault, OpenTelemetry instrumentation, and KQL queries.

No, and the two are easily confused. AI-102 covers designing and implementing Azure AI solutions using Azure AI services such as vision, language, and speech. AI-200 is about the cloud application engineering underneath AI workloads: containers, serverless, messaging, vector databases, secrets, and observability. Different exam, different certification, different job.

Still have questions?

Reach out to our learning advisors for personalized guidance on choosing the right course, group training, or enterprise packages.

📞 Talk to an Advisor

What You Get with Microtek Learning

Instructor-Led Excellence

✓ Certified Instructor-led Training
✓ Top Industry Trainers
✓ Official Student Handbooks

Measurable Learning Outcomes

✓ Pre- & Post-Training Assessments
✓ Practice Tests
✓ Exam-Oriented Curriculum

Real-World Skill Building

✓ Hands-on Activities & Scenarios
✓ Interactive Online Courses
✓ Peer Collaboration (Not in self-paced)

Full Support & Perks

✓ Exam Scheduling Support ^*
✓ Learn & Earn Program ^*
✓ Support from Certified Experts
✓ Gov. & Private Pricing ^*

Our Clients

For over 10 years, Microtek Learning has helped organizations, leaders, students and professionals to reach their maximum potential. We have led the path by addressing their challenges and advancing their performances.